Extended object tracking methods based on random matrices, founded on Bayesian filters, have been able to achieve efficient recursive processes while jointly estimating the kinematic states and extension of the targets. Existing random matrix approaches typically assume that the evolution of state and extension follows a first-order Markov process, where the current estimate of the target depends solely on the previous moment. However, in real-world scenarios, this assumption fails because the evolution of states and extension is usually non-Markovian. In this paper, we introduce a novel extended object tracking method: a Bayesian recursive neural network assisted by deep memory. Initially, we propose an equivalent model under a non-Markovian assumption and derive the implementation of its Bayesian filtering framework. Thereafter, Gaussian approximation and moment matching are employed to derive the analytical solution for the proposed Bayesian filtering framework. Finally, based on the closed-form solution, we design an end-to-end trainable Bayesian recursive neural network for extended object tracking. Experiment results on simulated and real-world datasets show that the proposed methods outperforms traditional extended object tracking methods and state-of-the-art deep learning approaches.
Fine-grained robot manipulation, such as lifting and rotating a bottle to display the label on the cap, requires robust reasoning about object parts and their relationships with intended tasks. Despite recent advances in training general-purpose robot manipulation policies guided by language instructions, there is a notable lack of large-scale datasets for fine-grained manipulation tasks with part-level instructions and diverse 3D object instances annotated with part-level labels. In this work, we introduce PartInstruct, the first large-scale benchmark for training and evaluating fine-grained robot manipulation models using part-level instructions. PartInstruct comprises 513 object instances across 14 categories, each annotated with part-level information, and 1302 fine-grained manipulation tasks organized into 16 task classes. Our training set consists of over 10,000 expert demonstrations synthesized in a 3D simulator, where each demonstration is paired with a high-level task instruction, a chain of base part-based skill instructions, and ground-truth 3D information about the object and its parts. Additionally, we designed a comprehensive test suite to evaluate the generalizability of learned policies across new states, objects, and tasks. We evaluated several state-of-the-art robot manipulation approaches, including end-to-end vision-language policy learning and bi-level planning models for robot manipulation on our benchmark. The experimental results reveal that current models struggle to robustly ground part concepts and predict actions in 3D space, and face challenges when manipulating object parts in long-horizon tasks.
Synthesizing whole-body manipulation of articulated objects, including body motion, hand motion, and object motion, is a critical yet challenging task with broad applications in virtual humans and robotics. The core challenges are twofold. First, achieving realistic whole-body motion requires tight coordination between the hands and the rest of the body, as their movements are interdependent during manipulation. Second, articulated object manipulation typically involves high degrees of freedom and demands higher precision, often requiring the fingers to be placed at specific regions to actuate movable parts. To address these challenges, we propose a novel coordinated diffusion noise optimization framework. Specifically, we perform noise-space optimization over three specialized diffusion models for the body, left hand, and right hand, each trained on its own motion dataset to improve generalization. Coordination naturally emerges through gradient flow along the human kinematic chain, allowing the global body posture to adapt in response to hand motion objectives with high fidelity. To further enhance precision in hand-object interaction, we adopt a unified representation based on basis point sets (BPS), where end-effector positions are encoded as distances to the same BPS used for object geometry. This unified representation captures fine-grained spatial relationships between the hand and articulated object parts, and the resulting trajectories serve as targets to guide the optimization of diffusion noise, producing highly accurate interaction motion. We conduct extensive experiments demonstrating that our method outperforms existing approaches in motion quality and physical plausibility, and enables various capabilities such as object pose control, simultaneous walking and manipulation, and whole-body generation from hand-only data.
We present an effective approach for adapting the Segment Anything Model 2 (SAM2) to the Visual Object Tracking (VOT) task. Our method leverages the powerful pre-trained capabilities of SAM2 and incorporates several key techniques to enhance its performance in VOT applications. By combining SAM2 with our proposed optimizations, we achieved a first place AUC score of 89.4 on the 2024 ICPR Multi-modal Object Tracking challenge, demonstrating the effectiveness of our approach. This paper details our methodology, the specific enhancements made to SAM2, and a comprehensive analysis of our results in the context of VOT solutions along with the multi-modality aspect of the dataset.
Cross-view geo-localization determines the location of a query image, captured by a drone or ground-based camera, by matching it to a geo-referenced satellite image. While traditional approaches focus on image-level localization, many applications, such as search-and-rescue, infrastructure inspection, and precision delivery, demand object-level accuracy. This enables users to prompt a specific object with a single click on a drone image to retrieve precise geo-tagged information of the object. However, variations in viewpoints, timing, and imaging conditions pose significant challenges, especially when identifying visually similar objects in extensive satellite imagery. To address these challenges, we propose an Object-level Cross-view Geo-localization Network (OCGNet). It integrates user-specified click locations using Gaussian Kernel Transfer (GKT) to preserve location information throughout the network. This cue is dually embedded into the feature encoder and feature matching blocks, ensuring robust object-specific localization. Additionally, OCGNet incorporates a Location Enhancement (LE) module and a Multi-Head Cross Attention (MHCA) module to adaptively emphasize object-specific features or expand focus to relevant contextual regions when necessary. OCGNet achieves state-of-the-art performance on a public dataset, CVOGL. It also demonstrates few-shot learning capabilities, effectively generalizing from limited examples, making it suitable for diverse applications (https://github.com/ZheyangH/OCGNet).
Accurate, fast, and reliable 3D perception is essential for autonomous driving. Recently, bird's-eye view (BEV)-based perception approaches have emerged as superior alternatives to perspective-based solutions, offering enhanced spatial understanding and more natural outputs for planning. Existing BEV-based 3D object detection methods, typically adhering to angle-based representation, directly estimate the size and orientation of rotated bounding boxes. We observe that BEV-based 3D object detection is analogous to aerial oriented object detection, where angle-based methods are recognized for being affected by discontinuities in their loss functions. Drawing inspiration from this domain, we propose Restricted Quadrilateral Representation to define 3D regression targets. RQR3D regresses the smallest horizontal bounding box encapsulating the oriented box, along with the offsets between the corners of these two boxes, thereby transforming the oriented object detection problem into a keypoint regression task. RQR3D is compatible with any 3D object detection approach. We employ RQR3D within an anchor-free single-stage object detection method and introduce an objectness head to address class imbalance problem. Furthermore, we introduce a simplified radar fusion backbone that eliminates the need for voxel grouping and processes the BEV-mapped point cloud with standard 2D convolutions, rather than sparse convolutions. Extensive evaluations on the nuScenes dataset demonstrate that RQR3D achieves state-of-the-art performance in camera-radar 3D object detection, outperforming the previous best method by +4% in NDS and +2.4% in mAP, and significantly reducing the translation and orientation errors, which are crucial for safe autonomous driving. These consistent gains highlight the robustness, precision, and real-world readiness of our approach.
Multimodal Large Language Models (MLLMs) have demonstrated strong performance in visual understanding tasks, yet they often suffer from object hallucinations--generating descriptions of objects that are inconsistent with or entirely absent from the input. This issue is closely related to dataset biases, where frequent co-occurrences of objects lead to entangled semantic representations across modalities. As a result, models may erroneously activate object representations that are commonly associated with the input but not actually present. To address this, we propose a causality-driven disentanglement framework that mitigates hallucinations through causal intervention. Our approach includes a Causal-Driven Projector in the visual pathway and a Causal Intervention Module integrated into the final transformer layer of the language model. These components work together to reduce spurious correlations caused by biased training data. Experimental results show that our method significantly reduces hallucinations while maintaining strong performance on multiple multimodal benchmarks. Visualization analyses further confirm improved separability of object representations. The code is available at: https://github.com/IgniSavium/Causal-LLaVA
While diffusion models excel at generating high-quality images, they often struggle with accurate counting, attributes, and spatial relationships in complex multi-object scenes. One potential approach is to utilize Multimodal Large Language Model (MLLM) as an AI agent to build a self-correction framework. However, these approaches are highly dependent on the capabilities of the employed MLLM, often failing to account for all objects within the image. To address these challenges, we propose Marmot, a novel and generalizable framework that employs Multi-Agent Reasoning for Multi-Object Self-Correcting, enhancing image-text alignment and facilitating more coherent multi-object image editing. Our framework adopts a divide-and-conquer strategy, decomposing the self-correction task into object-level subtasks according to three critical dimensions: counting, attributes, and spatial relationships. We construct a multi-agent self-correcting system featuring a decision-execution-verification mechanism, effectively mitigating inter-object interference and enhancing editing reliability. To resolve the problem of subtask integration, we propose a Pixel-Domain Stitching Smoother that employs mask-guided two-stage latent space optimization. This innovation enables parallel processing of subtask results, thereby enhancing runtime efficiency while eliminating multi-stage distortion accumulation. Extensive experiments demonstrate that Marmot significantly improves accuracy in object counting, attribute assignment, and spatial relationships for image generation tasks.
The motion of deformable 4D objects lies in a low-dimensional manifold. To better capture the low dimensionality and enable better controllability, traditional methods have devised several heuristic-based methods, i.e., rigging, for manipulating dynamic objects in an intuitive fashion. However, such representations are not scalable due to the need for expert knowledge of specific categories. Instead, we study the automatic exploration of such low-dimensional structures in a purely data-driven manner. Specifically, we design a novel representation that encodes deformable 4D objects into a sparse set of spatially grounded blobs and an instance-aware feature volume to disentangle the pose and instance information of the 3D shape. With such a representation, we can manipulate the pose of 3D objects intuitively by modifying the parameters of the blobs, while preserving rich instance-specific information. We evaluate the proposed method on a variety of object categories and demonstrate the effectiveness of the proposed framework. Project page: https://guangzhaohe.com/canor
Multi-modal object re-identification (ReID) aims to extract identity features across heterogeneous spectral modalities to enable accurate recognition and retrieval in complex real-world scenarios. However, most existing methods rely on implicit feature fusion structures, making it difficult to model fine-grained recognition strategies under varying challenging conditions. Benefiting from the powerful semantic understanding capabilities of Multi-modal Large Language Models (MLLMs), the visual appearance of an object can be effectively translated into descriptive text. In this paper, we propose a reliable multi-modal caption generation method based on attribute confidence, which significantly reduces the unknown recognition rate of MLLMs in multi-modal semantic generation and improves the quality of generated text. Additionally, we propose a novel ReID framework NEXT, the Multi-grained Mixture of Experts via Text-Modulation for Multi-modal Object Re-Identification. Specifically, we decouple the recognition problem into semantic and structural expert branches to separately capture modality-specific appearance and intrinsic structure. For semantic recognition, we propose the Text-Modulated Semantic-sampling Experts (TMSE), which leverages randomly sampled high-quality semantic texts to modulate expert-specific sampling of multi-modal features and mining intra-modality fine-grained semantic cues. Then, to recognize coarse-grained structure features, we propose the Context-Shared Structure-aware Experts (CSSE) that focuses on capturing the holistic object structure across modalities and maintains inter-modality structural consistency through a soft routing mechanism. Finally, we propose the Multi-Modal Feature Aggregation (MMFA), which adopts a unified feature fusion strategy to simply and effectively integrate semantic and structural expert outputs into the final identity representations.
In this work, we propose a progressive scaling training strategy for visual object tracking, systematically analyzing the influence of training data volume, model size, and input resolution on tracking performance. Our empirical study reveals that while scaling each factor leads to significant improvements in tracking accuracy, naive training suffers from suboptimal optimization and limited iterative refinement. To address this issue, we introduce DT-Training, a progressive scaling framework that integrates small teacher transfer and dual-branch alignment to maximize model potential. The resulting scaled tracker consistently outperforms state-of-the-art methods across multiple benchmarks, demonstrating strong generalization and transferability of the proposed method. Furthermore, we validate the broader applicability of our approach to additional tasks, underscoring its versatility beyond tracking.
Recent methods for zero-shot Human-Object Interaction (HOI) detection typically leverage the generalization ability of large Vision-Language Model (VLM), i.e., CLIP, on unseen categories, showing impressive results on various zero-shot settings. However, existing methods struggle to adapt CLIP representations for human-object pairs, as CLIP tends to overlook fine-grained information necessary for distinguishing interactions. To address this issue, we devise, LAIN, a novel zero-shot HOI detection framework enhancing the locality and interaction awareness of CLIP representations. The locality awareness, which involves capturing fine-grained details and the spatial structure of individual objects, is achieved by aggregating the information and spatial priors of adjacent neighborhood patches. The interaction awareness, which involves identifying whether and how a human is interacting with an object, is achieved by capturing the interaction pattern between the human and the object. By infusing locality and interaction awareness into CLIP representation, LAIN captures detailed information about the human-object pairs. Our extensive experiments on existing benchmarks show that LAIN outperforms previous methods on various zero-shot settings, demonstrating the importance of locality and interaction awareness for effective zero-shot HOI detection.
Multi-view multi-object tracking (MVMOT) has found widespread applications in intelligent transportation, surveillance systems, and urban management. However, existing studies rarely address genuinely free-viewpoint MVMOT systems, which could significantly enhance the flexibility and scalability of cooperative tracking systems. To bridge this gap, we first construct the Multi-Drone Multi-Object Tracking (MDMOT) dataset, captured by mobile drone swarms across diverse real-world scenarios, initially establishing the first benchmark for multi-object tracking in arbitrary multi-view environment. Building upon this foundation, we propose \textbf{FusionTrack}, an end-to-end framework that reasonably integrates tracking and re-identification to leverage multi-view information for robust trajectory association. Extensive experiments on our MDMOT and other benchmark datasets demonstrate that FusionTrack achieves state-of-the-art performance in both single-view and multi-view tracking.
Reasoning Video Object Segmentation is a challenging task, which generates a mask sequence from an input video and an implicit, complex text query. Existing works probe into the problem by finetuning Multimodal Large Language Models (MLLM) for segmentation-based output, while still falling short in difficult cases on videos given temporally-sensitive queries, primarily due to the failure to integrate temporal and spatial information. In this paper, we propose ThinkVideo, a novel framework which leverages the zero-shot Chain-of-Thought (CoT) capability of MLLM to address these challenges. Specifically, ThinkVideo utilizes the CoT prompts to extract object selectivities associated with particular keyframes, then bridging the reasoning image segmentation model and SAM2 video processor to output mask sequences. The ThinkVideo framework is training-free and compatible with closed-source MLLMs, which can be applied to Reasoning Video Instance Segmentation. We further extend the framework for online video streams, where the CoT is used to update the object of interest when a better target starts to emerge and becomes visible. We conduct extensive experiments on video object segmentation with explicit and implicit queries. The results show that ThinkVideo significantly outperforms previous works in both cases, qualitatively and quantitatively.
We present the Semantics-aware Dataset and Benchmark Generation Pipeline for Open-vocabulary Object Navigation in Dynamic Scenes (SD-OVON). It utilizes pretraining multimodal foundation models to generate infinite unique photo-realistic scene variants that adhere to real-world semantics and daily commonsense for the training and the evaluation of navigation agents, accompanied with a plugin for generating object navigation task episodes compatible to the Habitat simulator. In addition, we offer two pre-generated object navigation task datasets, SD-OVON-3k and SD-OVON-10k, comprising respectively about 3k and 10k episodes of the open-vocabulary object navigation task, derived from the SD-OVON-Scenes dataset with 2.5k photo-realistic scans of real-world environments and the SD-OVON-Objects dataset with 0.9k manually inspected scanned and artist-created manipulatable object models. Unlike prior datasets limited to static environments, SD-OVON covers dynamic scenes and manipulatable objects, facilitating both real-to-sim and sim-to-real robotic applications. This approach enhances the realism of navigation tasks, the training and the evaluation of open-vocabulary object navigation agents in complex settings. To demonstrate the effectiveness of our pipeline and datasets, we propose two baselines and evaluate them along with state-of-the-art baselines on SD-OVON-3k. The datasets, benchmark and source code are publicly available.
Humans interact with their world while leveraging precise full-body control to achieve versatile goals. This versatility allows them to solve long-horizon, underspecified problems, such as placing a cup in a sink, by seamlessly sequencing actions like approaching the cup, grasping, transporting it, and finally placing it in the sink. Such goal-driven control can enable new procedural tools for animation systems, enabling users to define partial objectives while the system naturally ``fills in'' the intermediate motions. However, while current methods for whole-body dexterous manipulation in physics-based animation achieve success in specific interaction tasks, they typically employ control paradigms (e.g., detailed kinematic motion tracking, continuous object trajectory following, or direct VR teleoperation) that offer limited versatility for high-level goal specification across the entire coupled human-object system. To bridge this gap, we present MaskedManipulator, a unified and generative policy developed through a two-stage learning approach. First, our system trains a tracking controller to physically reconstruct complex human-object interactions from large-scale human mocap datasets. This tracking controller is then distilled into MaskedManipulator, which provides users with intuitive control over both the character's body and the manipulated object. As a result, MaskedManipulator enables users to specify complex loco-manipulation tasks through intuitive high-level objectives (e.g., target object poses, key character stances), and MaskedManipulator then synthesizes the necessary full-body actions for a physically simulated humanoid to achieve these goals, paving the way for more interactive and life-like virtual characters.
Two sampling strategies are investigated to enhance efficiency in training a deep learning object detection model. These sampling strategies are employed under the assumption of Lipschitz continuity of deep learning models. The first strategy is uniform sampling which seeks to obtain samples evenly yet randomly through the state space of the object dynamics. The second strategy of frame difference sampling is developed to explore the temporal redundancy among successive frames in a video. Experiment result indicates that these proposed sampling strategies provide a dataset that yields good training performance while requiring relatively few manually labelled samples.
Embodied agents empowered by large language models (LLMs) have shown strong performance in household object rearrangement tasks. However, these tasks primarily focus on single-turn interactions with simplified instructions, which do not truly reflect the challenges of providing meaningful assistance to users. To provide personalized assistance, embodied agents must understand the unique semantics that users assign to the physical world (e.g., favorite cup, breakfast routine) by leveraging prior interaction history to interpret dynamic, real-world instructions. Yet, the effectiveness of embodied agents in utilizing memory for personalized assistance remains largely underexplored. To address this gap, we present MEMENTO, a personalized embodied agent evaluation framework designed to comprehensively assess memory utilization capabilities to provide personalized assistance. Our framework consists of a two-stage memory evaluation process design that enables quantifying the impact of memory utilization on task performance. This process enables the evaluation of agents' understanding of personalized knowledge in object rearrangement tasks by focusing on its role in goal interpretation: (1) the ability to identify target objects based on personal meaning (object semantics), and (2) the ability to infer object-location configurations from consistent user patterns, such as routines (user patterns). Our experiments across various LLMs reveal significant limitations in memory utilization, with even frontier models like GPT-4o experiencing a 30.5% performance drop when required to reference multiple memories, particularly in tasks involving user patterns. These findings, along with our detailed analyses and case studies, provide valuable insights for future research in developing more effective personalized embodied agents. Project website: https://connoriginal.github.io/MEMENTO
Traditional methods for 3D object compression operate only on structural information within the object vertices, polygons, and textures. These methods are effective at compression rates up to 10x for standard object sizes but quickly deteriorate at higher compression rates with texture artifacts, low-polygon counts, and mesh gaps. In contrast, semantic compression ignores structural information and operates directly on the core concepts to push to extreme levels of compression. In addition, it uses natural language as its storage format, which makes it natively human-readable and a natural fit for emerging applications built around large-scale, collaborative projects within augmented and virtual reality. It deprioritizes structural information like location, size, and orientation and predicts the missing information with state-of-the-art deep generative models. In this work, we construct a pipeline for 3D semantic compression from public generative models and explore the quality-compression frontier for 3D object compression. We apply this pipeline to achieve rates as high as 105x for 3D objects taken from the Objaverse dataset and show that semantic compression can outperform traditional methods in the important quality-preserving region around 100x compression.
Egocentric hand-object motion generation is crucial for immersive AR/VR and robotic imitation but remains challenging due to unstable viewpoints, self-occlusions, perspective distortion, and noisy ego-motion. Existing methods rely on predefined 3D object priors, limiting generalization to novel objects, which restricts their generalizability to novel objects. Meanwhile, recent multimodal approaches suffer from ambiguous generation from abstract textual cues, intricate pipelines for modeling 3D hand-object correlation, and compounding errors in open-loop prediction. We propose MEgoHand, a multimodal framework that synthesizes physically plausible hand-object interactions from egocentric RGB, text, and initial hand pose. MEgoHand introduces a bi-level architecture: a high-level "cerebrum" leverages a vision language model (VLM) to infer motion priors from visual-textual context and a monocular depth estimator for object-agnostic spatial reasoning, while a low-level DiT-based flow-matching policy generates fine-grained trajectories with temporal orthogonal filtering to enhance stability. To address dataset inconsistency, we design a dataset curation paradigm with an Inverse MANO Retargeting Network and Virtual RGB-D Renderer, curating a unified dataset of 3.35M RGB-D frames, 24K interactions, and 1.2K objects. Extensive experiments across five in-domain and two cross-domain datasets demonstrate the effectiveness of MEgoHand, achieving substantial reductions in wrist translation error (86.9%) and joint rotation error (34.1%), highlighting its capacity to accurately model fine-grained hand joint structures and generalize robustly across diverse scenarios.