We explore the task of language-guided video segmentation (LVS). Previous algorithms mostly adopt 3D CNNs to learn video representation, struggling to capture long-term context and easily suffering from visual-linguistic misalignment. In light of this, we present Locater (local-global context aware Transformer), which augments the Transformer architecture with a finite memory so as to query the entire video with the language expression in an efficient manner. The memory is designed to involve two components -- one for persistently preserving global video content, and one for dynamically gathering local temporal context and segmentation history. Based on the memorized local-global context and the particular content of each frame, Locater holistically and flexibly comprehends the expression as an adaptive query vector for each frame. The vector is used to query the corresponding frame for mask generation. The memory also allows Locater to process videos with linear time complexity and constant size memory, while Transformer-style self-attention computation scales quadratically with sequence length. To thoroughly examine the visual grounding capability of LVS models, we contribute a new LVS dataset, A2D-S+, which is built upon A2D-S dataset but poses increased challenges in disambiguating among similar objects. Experiments on three LVS datasets and our A2D-S+ show that Locater outperforms previous state-of-the-arts. Further, we won the 1st place in the Referring Video Object Segmentation Track of the 3rd Large-scale Video Object Segmentation Challenge, where Locater served as the foundation for the winning solution. Our code and dataset are available at: https://github.com/leonnnop/Locater
How to design proper training pairs is critical for super-resolving real-world low-quality (LQ) images, which suffers from the difficulties in either acquiring paired ground-truth high-quality (HQ) images or synthesizing photo-realistic degraded LQ observations. Recent works mainly focus on modeling the degradation with handcrafted or estimated degradation parameters, which are however incapable to model complicated real-world degradation types, resulting in limited quality improvement. Notably, LQ face images, which may have the same degradation process as natural images, can be robustly restored with photo-realistic textures by exploiting their strong structural priors. This motivates us to use the real-world LQ face images and their restored HQ counterparts to model the complex real-world degradation (namely ReDegNet), and then transfer it to HQ natural images to synthesize their realistic LQ counterparts. By taking these paired HQ-LQ face images as inputs to explicitly predict the degradation-aware and content-independent representations, we could control the degraded image generation, and subsequently transfer these degradation representations from face to natural images to synthesize the degraded LQ natural images. Experiments show that our ReDegNet can well learn the real degradation process from face images. The restoration network trained with our synthetic pairs performs favorably against SOTAs. More importantly, our method provides a new way to handle the real-world complex scenarios by learning their degradation representations from the facial portions, which can be used to significantly improve the quality of non-facial areas. The source code is available at https://github.com/csxmli2016/ReDegNet.
Predicting natural and diverse 3D hand gestures from the upper body dynamics is a practical yet challenging task in virtual avatar creation. Previous works usually overlook the asymmetric motions between two hands and generate two hands in a holistic manner, leading to unnatural results. In this work, we introduce a novel bilateral hand disentanglement based two-stage 3D hand generation method to achieve natural and diverse 3D hand prediction from body dynamics. In the first stage, we intend to generate natural hand gestures by two hand-disentanglement branches. Considering the asymmetric gestures and motions of two hands, we introduce a Spatial-Residual Memory (SRM) module to model spatial interaction between the body and each hand by residual learning. To enhance the coordination of two hand motions wrt. body dynamics holistically, we then present a Temporal-Motion Memory (TMM) module. TMM can effectively model the temporal association between body dynamics and two hand motions. The second stage is built upon the insight that 3D hand predictions should be non-deterministic given the sequential body postures. Thus, we further diversify our 3D hand predictions based on the initial output from the stage one. Concretely, we propose a Prototypical-Memory Sampling Strategy (PSS) to generate the non-deterministic hand gestures by gradient-based Markov Chain Monte Carlo (MCMC) sampling. Extensive experiments demonstrate that our method outperforms the state-of-the-art models on the B2H dataset and our newly collected TED Hands dataset. The dataset and code are available at https://github.com/XingqunQi-lab/Diverse-3D-Hand-Gesture-Prediction.
Program synthesis aims to create accurate, executable programs from problem specifications, specifically from natural language descriptions in our context. Recent studies have leveraged the power of reinforcement learning (RL) in conjunction with large language models (LLMs), significantly enhancing code generation capabilities. The application of RL focuses on directly optimizing for functional correctness, offering an advantage over conventional supervised methods. Despite policy-based RL methods dominating the literature on RL for program synthesis, the nature of program synthesis tasks hints at a natural alignment with value-based methods. This stems from the rich collection of off-policy programs, including those developed by human programmers and also historical samples, coupled with the straightforward verification of generated programs through automated unit testing, meaning rewards are easy to obtain. Diverging from the dominant use of policy-based algorithms, our work explores the feasibility of value-based approaches, leading to the development of our $\mathcal{B}$-Coder (pronounced Bellman coder). Yet, training value-based methods presents challenges due to the enormous search space inherent to program synthesis. To this end, we introduce an initialization protocol for RL agents utilizing pre-trained LMs and a conservative Bellman operator to reduce training complexities. Moreover, we demonstrate how to leverage the learned value functions as a dual strategy to post-process generated programs. Our empirical evaluations demonstrated $\mathcal{B}$-Coder's capability in achieving state-of-the-art performance when compared to policy-based methods. Remarkably, this achievement is reached with minimal reward engineering effort, highlighting the effectiveness of value-based RL, independent of reward designs.
Federated learning (FL) effectively mitigates the data silo challenge brought about by policies and privacy concerns, implicitly harnessing more data for deep model training. However, traditional centralized FL models grapple with diverse multi-center data, especially in the face of significant data heterogeneity, notably in medical contexts. In the realm of medical image segmentation, the growing imperative to curtail annotation costs has amplified the importance of weakly-supervised techniques which utilize sparse annotations such as points, scribbles, etc. A pragmatic FL paradigm shall accommodate diverse annotation formats across different sites, which research topic remains under-investigated. In such context, we propose a novel personalized FL framework with learnable prompt and aggregation (FedLPPA) to uniformly leverage heterogeneous weak supervision for medical image segmentation. In FedLPPA, a learnable universal knowledge prompt is maintained, complemented by multiple learnable personalized data distribution prompts and prompts representing the supervision sparsity. Integrated with sample features through a dual-attention mechanism, those prompts empower each local task decoder to adeptly adjust to both the local distribution and the supervision form. Concurrently, a dual-decoder strategy, predicated on prompt similarity, is introduced for enhancing the generation of pseudo-labels in weakly-supervised learning, alleviating overfitting and noise accumulation inherent to local data, while an adaptable aggregation method is employed to customize the task decoder on a parameter-wise basis. Extensive experiments on four distinct medical image segmentation tasks involving different modalities underscore the superiority of FedLPPA, with its efficacy closely parallels that of fully supervised centralized training. Our code and data will be available.
Large language models (LLMs) have shown impressive potential in helping with numerous medical challenges. Deploying LLMs in high-stakes applications such as medicine, however, brings in many concerns. One major area of concern relates to biased behaviors of LLMs in medical applications, leading to unfair treatment of individuals. To pave the way for the responsible and impactful deployment of Med LLMs, rigorous evaluation is a key prerequisite. Due to the huge complexity and variability of different medical scenarios, existing work in this domain has primarily relied on using manually crafted datasets for bias evaluation. In this study, we present a new method to scale up such bias evaluations by automatically generating test cases based on rigorous medical evidence. We specifically target the challenges of a) domain-specificity of bias characterization, b) hallucinating while generating the test cases, and c) various dependencies between the health outcomes and sensitive attributes. To that end, we offer new methods to address these challenges integrated with our generative pipeline, using medical knowledge graphs, medical ontologies, and customized general LLM evaluation frameworks in our method. Through a series of extensive experiments, we show that the test cases generated by our proposed method can effectively reveal bias patterns in Med LLMs at larger and more flexible scales than human-crafted datasets. We publish a large bias evaluation dataset using our pipeline, which is dedicated to a few medical case studies. A live demo of our application for vignette generation is available at https://vignette.streamlit.app. Our code is also available at https://github.com/healthylaife/autofair.
Gesture recognition is an important research area in the field of computer vision. Most gesture recognition efforts focus on close-set scenarios, thereby limiting the capacity to effectively handle unseen or novel gestures. We aim to address class-incremental gesture recognition, which entails the ability to accommodate new and previously unseen gestures over time. Specifically, we introduce a Prototype-Guided Pseudo Feature Replay (PGPFR) framework for data-free class-incremental gesture recognition. This framework comprises four components: Pseudo Feature Generation with Batch Prototypes (PFGBP), Variational Prototype Replay (VPR) for old classes, Truncated Cross-Entropy (TCE) for new classes, and Continual Classifier Re-Training (CCRT). To tackle the issue of catastrophic forgetting, the PFGBP dynamically generates a diversity of pseudo features in an online manner, leveraging class prototypes of old classes along with batch class prototypes of new classes. Furthermore, the VPR enforces consistency between the classifier's weights and the prototypes of old classes, leveraging class prototypes and covariance matrices to enhance robustness and generalization capabilities. The TCE mitigates the impact of domain differences of the classifier caused by pseudo features. Finally, the CCRT training strategy is designed to prevent overfitting to new classes and ensure the stability of features extracted from old classes. Extensive experiments conducted on two widely used gesture recognition datasets, namely SHREC 2017 3D and EgoGesture 3D, demonstrate that our approach outperforms existing state-of-the-art methods by 11.8\% and 12.8\% in terms of mean global accuracy, respectively. The code is available on https://github.com/sunao-101/PGPFR-3/.
얼굴 움직임과 표정은 대면 의사소통의 핵심으로, 발화와 함께 발언권 교환, 주의, 동의, 참여를 전달한다. 음성 기반 얼굴 애니메이션은 입술 동기화와 오디오 조건부 모션 생성에서 큰 진전을 이루었지만, 대부분의 방법은 대화 행동을 오디오의 창발적(emergent) 부산물로 취급하거나, 거친 시퀀스 수준의 정서(affect) 제어만 제공한다. 그 결과, 시선 접촉과 회피, 리듬감 있는 머리 움직임, 감정과 같은 핵심 비언어적 채널은 명시적으로 제어하기 어렵다. 우리는 반응형 대화 헤드 아바타를 위한 제어 가능한 3D 대화형(dyadic) 모션 사전(prior)인 STEER를 제시한다. STEER는 대화 행동을 시선, 머리 리듬, 감정에 대한 명시적 제어로 분해하여, 사용자가 아바타가 대화 상대를 어떻게 듣고, 반응하고, 교류하는지 조향할 수 있게 한다. 이러한 행동에 대한 시간 정렬 주석이 공개 대화형 코퍼스에서 제공되지 않기 때문에, 우리는 in-the-wild 대화형 영상에서 행동 의사 라벨(pseudo-label)을 복원하는 추적 및 주석 파이프라인을 도입한다. 인과적(causal) flow-matching 트랜스포머가 오디오, 상대 모션, 감정 및 제안된 행동 제어를 조건으로 하는 상대 인식(partner-aware) 목표 모션을 학습한다. 우리는 추적된 파라메트릭 모션을 아바타 구동 공간으로 매핑하는 학습된 매핑으로 Universal Gaussian Head-Avatar Prior를 확장하여, STEER를 사실적인(photorealistic) 아바타 파이프라인에 통합한다. 이를 통해 기본 아바타 모델을 재학습하지 않고도 고품질 Gaussian 헤드 아바타의 제어 가능한 애니메이션이 가능해진다. STEER는 모션 품질, 역학(dynamics), 다양성에서 최근 대화형 모션 베이스라인을 능가하고, 상대 결합(partner coupling)에서는 경쟁력을 유지하며, 시선, 머리 리듬, 감정 편집과 대화형 실시간 배포를 함께 가능하게 한다. 코드와 데이터셋 주석은 웹페이지에서 공개한다.
대규모 언어 모델 기반 멀티 에이전트 시스템은 최근 복잡한 장기(long-horizon) 과업에서 강력한 잠재력을 보여 왔다. 그러나 기존 방법은 주로 다양한 하위 작업에 대한 매개변수 적응 없이 거친 수준의 프롬프트 차원 구분에 의존하며, 그 결과 에이전트 간 이질성이 충분하지 않고 전문화된 역량이 제한되어 복잡한 요구 사항을 가진 과업에서 성능의 병목이 발생한다. 이를 해결하기 위해 본 논문에서는 과업 구조와 매개변수 수준 모두에서 (역할, 하위 작업) 조건부 전문화로 에이전트를 구분하는 과업 지향 멀티 에이전트 시스템인 MoRSE(Task-Oriented Multi-Agent System with Mixture of Role-Subtask Experts)를 제안한다. 과업 구조 수준에서 에이전트의 책임을 명확히 하기 위해, 각 과업을 의존성을 고려한 하위 작업의 방향성 비순환 그래프(Directed Acyclic Graph)로 분해하고 각 에이전트에 특정 (역할, 하위 작업)을 할당하는 과업 지향 멀티 에이전트 시스템을 정식화하여, 협업하는 에이전트 전반에 과업 수준의 전문화를 도입한다. 또한 다양한 역할 및 하위 작업의 매개변수 적응 요구를 해결하기 위해, 하위 작업을 위한 프로토타입 기반 의미 라우터(semantic router)를 갖춘 동적 (역할, 하위 작업) LoRA 전문가 혼합 모듈을 제안하며, 이를 통해 공유 LLM 기반 위에서 비용 효율적으로 에이전트에 매개변수 수준의 전문화를 더한다. 이어서, 희소한 과업 보상 하에서 전문가와 라우터를 안정적으로 함께 최적화하기 위해, 라우팅 결정으로 인해 발생하는 경로 간 분산으로부터 전문가 업데이트를 분리하여 전문가 품질과 라우팅 품질을 분리하는 2층 크레딧 할당(two-layer credit assignment)을 갖춘 계층적 그룹 상대 정책 최적화(hierarchical group-relative policy optimization)를 추가로 제안한다. 세 가지 백본에 걸친 코드 생성 벤치마크 실험을 통해 제안 방법의 효과를 입증하였으며, 전체 과업 성능과 단계별 성능이 모두 향상되었고, 학습된 전문화로부터 얻은 이득은 보류(held-out)된 과업 범주와 도메인 전반으로 일반화된다.
텍스트 형태의 과제 지침이 주어졌을 때, 단계별 시각적 지침을 이미지 시퀀스로 생성하려면 여러 속성을 동시에 만족해야 하며, 구체적으로는 단계 충실도(step faithfulness), 이미지 간 일관성(cross-image consistency), 프레임별 시각적 품질(per-frame visual quality)이 그렇다. 기존 텍스트-이미지(text-to-image) 생성 접근법은 독립 샘플링으로 일관성이 깨지고, 저품질 동영상에 대한 파인튜닝(fine-tuning)으로 프레임별 품질이 저하되며, 고정된 백본이 다단계 이해를 갖추지 못해 이 세 가지를 모두 충족하는 경우가 드물다. 본 연구에서는 InstructionCrafter를 제안한다. 이는 (1) 공간 고정(spatial-freeze) 학습과 (2) 지침 인식(instruction-aware) 어댑터를 통해 시간적·지침 정렬(alignment) 최적화와 프레임별 시각적 품질 최적화를 분리하는 것을 핵심 아이디어로 하는 diffusion 기반 프레임워크이다. 사전학습(pre-training)된 비디오 diffusion 백본 위에 InstructionCrafter는 프레임별 디테일을 제어하는 공간 레이어를 고정하고 시간적 경로와 텍스트 조건화 경로만 갱신하여 지침 의미와 단계 간 관계를 학습함으로써, 프레임별 품질을 위한 생성 사전(prior)을 보존하고 전체 파인튜닝 대비 학습 가능 파라미터를 약 50% 줄인다. 또한 모델의 지침 맥락 이해를 강화하는 두 가지 경량 어댑터를 도입한다. Consistent Adapter는 전체 지침 시퀀스와 인접 단계의 텍스트 단서를 집약하여 프레임 간 객체 정체성과 속성의 일관성을 유지하고, Context-Aware Temporal Adapter는 cross-attention 출력을 temporal self-attention의 bias로 변환하여 프레임 간 관계를 명시적으로 전파한다. 두 벤치마크(benchmark) 데이터셋(dataset)에 대한 광범위한 실험에서, 단계 충실도·이미지 간 일관성·프레임별 시각적 품질 전반에 걸쳐 최신(state-of-the-art) 수준의 성능을 보이면서 노이즈, 블러, 잘못된 자막을 크게 줄였음을 보였다. 코드와 학습된 모델은 공개될 예정이다.
In this paper, we address the problem of answering complex information needs by conversing conversations with search engines, in the sense that users can express their queries in natural language, and directly receivethe information they need from a short system response in a conversational manner. Recently, there have been some attempts towards a similar goal, e.g., studies on Conversational Agents (CAs) and Conversational Search (CS). However, they either do not address complex information needs, or they are limited to the development of conceptual frameworks and/or laboratory-based user studies. We pursue two goals in this paper: (1) the creation of a suitable dataset, the Search as a Conversation (SaaC) dataset, for the development of pipelines for conversations with search engines, and (2) the development of astate-of-the-art pipeline for conversations with search engines, the Conversations with Search Engines (CaSE), using this dataset. SaaC is built based on a multi-turn conversational search dataset, where we further employ workers from a crowdsourcing platform to summarize each relevant passage into a short, conversational response. CaSE enhances the state-of-the-art by introducing a supporting token identification module and aprior-aware pointer generator, which enables us to generate more accurate responses. We carry out experiments to show that CaSE is able to outperform strong baselines. We also conduct extensive analyses on the SaaC dataset to show where there is room for further improvement beyond CaSE. Finally, we release the SaaC dataset and the code for CaSE and all models used for comparison to facilitate future research on this topic.
Deep Learning approaches based on Convolutional Neural Networks (CNNs) are extensively utilized and very successful in a wide range of application areas, including image classification and speech recognition. For the execution of trained CNNs, i.e. model inference, we nowadays witness a shift from the Cloud to the Edge. Unfortunately, deploying and inferring large, compute and memory intensive CNNs on edge devices is challenging because these devices typically have limited power budgets and compute/memory resources. One approach to address this challenge is to leverage all available resources across multiple edge devices to deploy and execute a large CNN by properly partitioning the CNN and running each CNN partition on a separate edge device. Although such distribution, deployment, and execution of large CNNs on multiple edge devices is a desirable and beneficial approach, there currently does not exist a design and programming framework that takes a trained CNN model, together with a CNN partitioning specification, and fully automates the CNN model splitting and deployment on multiple edge devices to facilitate distributed CNN inference at the Edge. Therefore, in this paper, we propose a novel framework, called AutoDiCE, for automated splitting of a CNN model into a set of sub-models and automated code generation for distributed and collaborative execution of these sub-models on multiple, possibly heterogeneous, edge devices, while supporting the exploitation of parallelism among and within the edge devices. Our experimental results show that AutoDiCE can deliver distributed CNN inference with reduced energy consumption and memory usage per edge device, and improved overall system throughput at the same time.
Many applications of reinforcement learning can be formalized as goal-conditioned environments, where, in each episode, there is a "goal" that affects the rewards obtained during that episode but does not affect the dynamics. Various techniques have been proposed to improve performance in goal-conditioned environments, such as automatic curriculum generation and goal relabeling. In this work, we explore a connection between off-policy reinforcement learning in goal-conditioned settings and knowledge distillation. In particular: the current Q-value function and the target Q-value estimate are both functions of the goal, and we would like to train the Q-value function to match its target for all goals. We therefore apply Gradient-Based Attention Transfer (Zagoruyko and Komodakis 2017), a knowledge distillation technique, to the Q-function update. We empirically show that this can improve the performance of goal-conditioned off-policy reinforcement learning when the space of goals is high-dimensional. We also show that this technique can be adapted to allow for efficient learning in the case of multiple simultaneous sparse goals, where the agent can attain a reward by achieving any one of a large set of objectives, all specified at test time. Finally, to provide theoretical support, we give examples of classes of environments where (under some assumptions) standard off-policy algorithms such as DDPG require at least O(d^2) replay buffer transitions to learn an optimal policy, while our proposed technique requires only O(d) transitions, where d is the dimensionality of the goal and state space. Code is available at https://github.com/alevine0/ReenGAGE.
Natural-language dialog is key for intuitive human-robot interaction. It can be used not only to express humans' intents, but also to communicate instructions for improvement if a robot does not understand a command correctly. Of great importance is to endow robots with the ability to learn from such interaction experience in an incremental way to allow them to improve their behaviors or avoid mistakes in the future. In this paper, we propose a system to achieve incremental learning of complex behavior from natural interaction, and demonstrate its implementation on a humanoid robot. Building on recent advances, we present a system that deploys Large Language Models (LLMs) for high-level orchestration of the robot's behavior, based on the idea of enabling the LLM to generate Python statements in an interactive console to invoke both robot perception and action. The interaction loop is closed by feeding back human instructions, environment observations, and execution results to the LLM, thus informing the generation of the next statement. Specifically, we introduce incremental prompt learning, which enables the system to interactively learn from its mistakes. For that purpose, the LLM can call another LLM responsible for code-level improvements of the current interaction based on human feedback. The improved interaction is then saved in the robot's memory, and thus retrieved on similar requests. We integrate the system in the robot cognitive architecture of the humanoid robot ARMAR-6 and evaluate our methods both quantitatively (in simulation) and qualitatively (in simulation and real-world) by demonstrating generalized incrementally-learned knowledge.
Collaborative Filtering (CF) recommender models highly depend on user-item interactions to learn CF representations, thus falling short of recommending cold-start items. To address this issue, prior studies mainly introduce item features (e.g., thumbnails) for cold-start item recommendation. They learn a feature extractor on warm-start items to align feature representations with interactions, and then leverage the feature extractor to extract the feature representations of cold-start items for interaction prediction. Unfortunately, the features of cold-start items, especially the popular ones, tend to diverge from those of warm-start ones due to temporal feature shifts, preventing the feature extractor from accurately learning feature representations of cold-start items. To alleviate the impact of temporal feature shifts, we consider using Distributionally Robust Optimization (DRO) to enhance the generation ability of the feature extractor. Nonetheless, existing DRO methods face an inconsistency issue: the worse-case warm-start items emphasized during DRO training might not align well with the cold-start item distribution. To capture the temporal feature shifts and combat this inconsistency issue, we propose a novel temporal DRO with new optimization objectives, namely, 1) to integrate a worst-case factor to improve the worst-case performance, and 2) to devise a shifting factor to capture the shifting trend of item features and enhance the optimization of the potentially popular groups in cold-start items. Substantial experiments on three real-world datasets validate the superiority of our temporal DRO in enhancing the generalization ability of cold-start recommender models. The code is available at https://github.com/Linxyhaha/TDRO/.
Roadside perception can greatly increase the safety of autonomous vehicles by extending their perception ability beyond the visual range and addressing blind spots. However, current state-of-the-art vision-based roadside detection methods possess high accuracy on labeled scenes but have inferior performance on new scenes. This is because roadside cameras remain stationary after installation and can only collect data from a single scene, resulting in the algorithm overfitting these roadside backgrounds and camera poses. To address this issue, in this paper, we propose an innovative Scenario Generalization Framework for Vision-based Roadside 3D Object Detection, dubbed SGV3D. Specifically, we employ a Background-suppressed Module (BSM) to mitigate background overfitting in vision-centric pipelines by attenuating background features during the 2D to bird's-eye-view projection. Furthermore, by introducing the Semi-supervised Data Generation Pipeline (SSDG) using unlabeled images from new scenes, diverse instance foregrounds with varying camera poses are generated, addressing the risk of overfitting specific camera poses. We evaluate our method on two large-scale roadside benchmarks. Our method surpasses all previous methods by a significant margin in new scenes, including +42.57% for vehicle, +5.87% for pedestrian, and +14.89% for cyclist compared to BEVHeight on the DAIR-V2X-I heterologous benchmark. On the larger-scale Rope3D heterologous benchmark, we achieve notable gains of 14.48% for car and 12.41% for large vehicle. We aspire to contribute insights on the exploration of roadside perception techniques, emphasizing their capability for scenario generalization. The code will be available at https://github.com/yanglei18/SGV3D
As machine learning (ML) algorithms get deployed in an ever-increasing number of applications, these algorithms need to achieve better trade-offs between high accuracy, high throughput and low latency. This paper introduces NASH, a novel approach that applies neural architecture search to machine learning hardware. Using NASH, hardware designs can achieve not only high throughput and low latency but also superior accuracy performance. We present four versions of the NASH strategy in this paper, all of which show higher accuracy than the original models. The strategy can be applied to various convolutional neural networks, selecting specific model operations among many to guide the training process toward higher accuracy. Experimental results show that applying NASH on ResNet18 or ResNet34 achieves a top 1 accuracy increase of up to 3.1% and a top 5 accuracy increase of up to 2.2% compared to the non-NASH version when tested on the ImageNet data set. We also integrated this approach into the FINN hardware model synthesis tool to automate the application of our approach and the generation of the hardware model. Results show that using FINN can achieve a maximum throughput of 324.5 fps. In addition, NASH models can also result in a better trade-off between accuracy and hardware resource utilization. The accuracy-hardware (HW) Pareto curve shows that the models with the four NASH versions represent the best trade-offs achieving the highest accuracy for a given HW utilization. The code for our implementation is open-source and publicly available on GitHub at https://github.com/MFJI/NASH.
Speech-driven gesture generation is an emerging field within virtual human creation. However, a significant challenge lies in accurately determining and processing the multitude of input features (such as acoustic, semantic, emotional, personality, and even subtle unknown features). Traditional approaches, reliant on various explicit feature inputs and complex multimodal processing, constrain the expressiveness of resulting gestures and limit their applicability. To address these challenges, we present Persona-Gestor, a novel end-to-end generative model designed to generate highly personalized 3D full-body gestures solely relying on raw speech audio. The model combines a fuzzy feature extractor and a non-autoregressive Adaptive Layer Normalization (AdaLN) transformer diffusion architecture. The fuzzy feature extractor harnesses a fuzzy inference strategy that automatically infers implicit, continuous fuzzy features. These fuzzy features, represented as a unified latent feature, are fed into the AdaLN transformer. The AdaLN transformer introduces a conditional mechanism that applies a uniform function across all tokens, thereby effectively modeling the correlation between the fuzzy features and the gesture sequence. This module ensures a high level of gesture-speech synchronization while preserving naturalness. Finally, we employ the diffusion model to train and infer various gestures. Extensive subjective and objective evaluations on the Trinity, ZEGGS, and BEAT datasets confirm our model's superior performance to the current state-of-the-art approaches. Persona-Gestor improves the system's usability and generalization capabilities, setting a new benchmark in speech-driven gesture synthesis and broadening the horizon for virtual human technology. Supplementary videos and code can be accessed at https://zf223669.github.io/Diffmotion-v2-website/
Recent advancements in Large Language Models (LLMs) have led to the development of Video Large Multi-modal Models (Video-LMMs) that can handle a wide range of video understanding tasks. These models have the potential to be deployed in real-world applications such as robotics, AI assistants, medical surgery, and autonomous vehicles. The widespread adoption of Video-LMMs in our daily lives underscores the importance of ensuring and evaluating their robust performance in mirroring human-like reasoning and interaction capabilities in complex, real-world contexts. However, existing benchmarks for Video-LMMs primarily focus on general video comprehension abilities and neglect assessing their reasoning capabilities over complex videos in the real-world context, and robustness of these models through the lens of user prompts as text queries. In this paper, we present the Complex Video Reasoning and Robustness Evaluation Suite (CVRR-ES), a novel benchmark that comprehensively assesses the performance of Video-LMMs across 11 diverse real-world video dimensions. We evaluate 9 recent models, including both open-source and closed-source variants, and find that most of the Video-LMMs, especially open-source ones, struggle with robustness and reasoning when dealing with complex videos. Based on our analysis, we develop a training-free Dual-Step Contextual Prompting (DSCP) technique to enhance the performance of existing Video-LMMs. Our findings provide valuable insights for building the next generation of human-centric AI systems with advanced robustness and reasoning capabilities. Our dataset and code are publicly available at: https://mbzuai-oryx.github.io/CVRR-Evaluation-Suite/.
Curvilinear object segmentation plays a crucial role across various applications, yet datasets in this domain often suffer from small scale due to the high costs associated with data acquisition and annotation. To address these challenges, this paper introduces a novel approach for expanding curvilinear object segmentation datasets, focusing on enhancing the informativeness of generated data and the consistency between semantic maps and generated images. Our method enriches synthetic data informativeness by generating curvilinear objects through their multiple textual features. By combining textual features from each sample in original dataset, we obtain synthetic images that beyond the original dataset's distribution. This initiative necessitated the creation of the Curvilinear Object Segmentation based on Text Generation (COSTG) dataset. Designed to surpass the limitations of conventional datasets, COSTG incorporates not only standard semantic maps but also some textual descriptions of curvilinear object features. To ensure consistency between synthetic semantic maps and images, we introduce the Semantic Consistency Preserving ControlNet (SCP ControlNet). This involves an adaptation of ControlNet with Spatially-Adaptive Normalization (SPADE), allowing it to preserve semantic information that would typically be washed away in normalization layers. This modification facilitates more accurate semantic image synthesis. Experimental results demonstrate the efficacy of our approach across three types of curvilinear objects (angiography, crack and retina) and six public datasets (CHUAC, XCAD, DCA1, DRIVE, CHASEDB1 and Crack500). The synthetic data generated by our method not only expand the dataset, but also effectively improves the performance of other curvilinear object segmentation models. Source code and dataset are available at \url{https://github.com/tanlei0/COSTG}.