Combining different sensing modalities with multiple positions helps form a unified perception and understanding of complex situations such as human behavior. Hence, human activity recognition (HAR) benefits from combining redundant and complementary information (Unimodal/Multimodal). Even so, it is not an easy task. It requires a multidisciplinary approach, including expertise in sensor technologies, signal processing, data fusion algorithms, and domain-specific knowledge. This Ph.D. work employs sensing modalities such as inertial, pressure (audio and atmospheric pressure), and textile capacitive sensing for HAR. The scenarios explored are gesture and hand position tracking, facial and head pattern recognition, and body posture and gesture recognition. The selected wearable devices and sensing modalities are fully integrated with machine learning-based algorithms, some of which are implemented in the embedded device, on the edge, and tested in real-time.
Smart factories leverage advanced technologies to optimize manufacturing processes and enhance efficiency. Implementing worker tracking systems, primarily through camera-based methods, ensures accurate monitoring. However, concerns about worker privacy and technology protection make it necessary to explore alternative approaches. We propose a non-visual, scalable solution using Bluetooth Low Energy (BLE) and ultrasound coordinates. BLE position estimation offers a very low-power and cost-effective solution, as the technology is available on smartphones and is scalable due to the large number of smartphone users, facilitating worker localization and safety protocol transmission. Ultrasound signals provide faster response times and higher accuracy but require custom hardware, increasing costs. To combine the benefits of both modalities, we employ knowledge distillation (KD) from ultrasound signals to BLE RSSI data. Once the student model is trained, the model only takes as inputs the BLE-RSSI data for inference, retaining the advantages of ubiquity and low cost of BLE RSSI. We tested our approach using data from an experiment with twelve participants in a smart factory test bed environment. We obtained an increase of 11.79% in the F1-score compared to the baseline (target model without KD and trained with BLE-RSSI data only).
Unsupervised constrained text generation aims to generate text under a given set of constraints without any supervised data. Current state-of-the-art methods stochastically sample edit positions and actions, which may cause unnecessary search steps. In this paper, we propose PMCTG to improve effectiveness by searching for the best edit position and action in each step. Specifically, PMCTG extends perturbed masking technique to effectively search for the most incongruent token to edit. Then it introduces four multi-aspect scoring functions to select edit action to further reduce search difficulty. Since PMCTG does not require supervised data, it could be applied to different generation tasks. We show that under the unsupervised setting, PMCTG achieves new state-of-the-art results in two representative tasks, namely keywords-to-sentence generation and paraphrasing.
The prevalent approaches of unsupervised 3D object detection follow cluster-based pseudo-label generation and iterative self-training processes. However, the challenge arises due to the sparsity of LiDAR scans, which leads to pseudo-labels with erroneous size and position, resulting in subpar detection performance. To tackle this problem, this paper introduces a Commonsense Prototype-based Detector, termed CPD, for unsupervised 3D object detection. CPD first constructs Commonsense Prototype (CProto) characterized by high-quality bounding box and dense points, based on commonsense intuition. Subsequently, CPD refines the low-quality pseudo-labels by leveraging the size prior from CProto. Furthermore, CPD enhances the detection accuracy of sparsely scanned objects by the geometric knowledge from CProto. CPD outperforms state-of-the-art unsupervised 3D detectors on Waymo Open Dataset (WOD), PandaSet, and KITTI datasets by a large margin. Besides, by training CPD on WOD and testing on KITTI, CPD attains 90.85% and 81.01% 3D Average Precision on easy and moderate car classes, respectively. These achievements position CPD in close proximity to fully supervised detectors, highlighting the significance of our method. The code will be available at https://github.com/hailanyi/CPD.
We introduce a novel and flexible framework for constructing locally adaptive Hamiltonian Monte Carlo (HMC) samplers by Gibbs sampling the algorithm's tuning parameters conditionally based on the position and momentum at each step. For adaptively sampling path lengths, our Gibbs self-tuning (GIST) approach encompasses randomized HMC, multinomial HMC, the No-U-Turn Sampler (NUTS), and the Apogee-to-Apogee Path Sampler as special cases. We exemplify the GIST framework with a novel alternative to NUTS for locally adapting path lengths, evaluated with an exact Hamiltonian for a high-dimensional, ill-conditioned Gaussian measure and with the leapfrog integrator for a suite of diverse models.
This position paper concerns the use of religious texts in Natural Language Processing (NLP), which is of special interest to the Ethics of NLP. Religious texts are expressions of culturally important values, and machine learned models have a propensity to reproduce cultural values encoded in their training data. Furthermore, translations of religious texts are frequently used by NLP researchers when language data is scarce. This repurposes the translations from their original uses and motivations, which often involve attracting new followers. This paper argues that NLP's use of such texts raises considerations that go beyond model biases, including data provenance, cultural contexts, and their use in proselytism. We argue for more consideration of researcher positionality, and of the perspectives of marginalized linguistic and religious communities.
Panoramic distortion poses a significant challenge in 360 depth estimation, particularly pronounced at the north and south poles. Existing methods either adopt a bi-projection fusion strategy to remove distortions or model long-range dependencies to capture global structures, which can result in either unclear structure or insufficient local perception. In this paper, we propose a spherical geometry transformer, named SGFormer, to address the above issues, with an innovative step to integrate spherical geometric priors into vision transformers. To this end, we retarget the transformer decoder to a spherical prior decoder (termed SPDecoder), which endeavors to uphold the integrity of spherical structures during decoding. Concretely, we leverage bipolar re-projection, circular rotation, and curve local embedding to preserve the spherical characteristics of equidistortion, continuity, and surface distance, respectively. Furthermore, we present a query-based global conditional position embedding to compensate for spatial structure at varying resolutions. It not only boosts the global perception of spatial position but also sharpens the depth structure across different patches. Finally, we conduct extensive experiments on popular benchmarks, demonstrating our superiority over state-of-the-art solutions.
Providing a measure of market risk is an important issue for investors and financial institutions. However, the existing models for this purpose are per definition symmetric. The current paper introduces an asymmetric capital asset pricing model for measurement of the market risk. It explicitly accounts for the fact that falling prices determine the risk for a long position in the risky asset and the rising prices govern the risk for a short position. Thus, a position dependent market risk measure that is provided accords better with reality. The empirical application reveals that Apple stock is more volatile than the market only for the short seller. Surprisingly, the investor that has a long position in this stock is facing a lower volatility than the market. This property is not captured by the standard asset pricing model, which has important implications for the expected returns and hedging designs.
The intrinsic alignments (IA) of galaxies, regarded as a contaminant in weak lensing analyses, represents the correlation of galaxy shapes due to gravitational tidal interactions and galaxy formation processes. As such, understanding IA is paramount for accurate cosmological inferences from weak lensing surveys; however, one limitation to our understanding and mitigation of IA is expensive simulation-based modeling. In this work, we present a deep learning approach to emulate galaxy position-position ($\xi$), position-orientation ($\omega$), and orientation-orientation ($\eta$) correlation function measurements and uncertainties from halo occupation distribution-based mock galaxy catalogs. We find strong Pearson correlation values with the model across all three correlation functions and further predict aleatoric uncertainties through a mean-variance estimation training procedure. $\xi(r)$ predictions are generally accurate to $\leq10\%$. Our model also successfully captures the underlying signal of the noisier correlations $\omega(r)$ and $\eta(r)$, although with a lower average accuracy. We find that the model performance is inhibited by the stochasticity of the data, and will benefit from correlations averaged over multiple data realizations. Our code will be made open source upon journal publication.
Many robot manipulation tasks can be framed as geometric reasoning tasks, where an agent must be able to precisely manipulate an object into a position that satisfies the task from a set of initial conditions. Often, task success is defined based on the relationship between two objects - for instance, hanging a mug on a rack. In such cases, the solution should be equivariant to the initial position of the objects as well as the agent, and invariant to the pose of the camera. This poses a challenge for learning systems which attempt to solve this task by learning directly from high-dimensional demonstrations: the agent must learn to be both equivariant as well as precise, which can be challenging without any inductive biases about the problem. In this work, we propose a method for precise relative pose prediction which is provably SE(3)-equivariant, can be learned from only a few demonstrations, and can generalize across variations in a class of objects. We accomplish this by factoring the problem into learning an SE(3) invariant task-specific representation of the scene and then interpreting this representation with novel geometric reasoning layers which are provably SE(3) equivariant. We demonstrate that our method can yield substantially more precise placement predictions in simulated placement tasks than previous methods trained with the same amount of data, and can accurately represent relative placement relationships data collected from real-world demonstrations. Supplementary information and videos can be found at https://sites.google.com/view/reldist-iclr-2023.
Zero-shot anomaly detection (ZSAD) methods entail detecting anomalies directly without access to any known normal or abnormal samples within the target item categories. Existing approaches typically rely on the robust generalization capabilities of multimodal pretrained models, computing similarities between manually crafted textual features representing "normal" or "abnormal" semantics and image features to detect anomalies and localize anomalous patches. However, the generic descriptions of "abnormal" often fail to precisely match diverse types of anomalies across different object categories. Additionally, computing feature similarities for single patches struggles to pinpoint specific locations of anomalies with various sizes and scales. To address these issues, we propose a novel ZSAD method called FiLo, comprising two components: adaptively learned Fine-Grained Description (FG-Des) and position-enhanced High-Quality Localization (HQ-Loc). FG-Des introduces fine-grained anomaly descriptions for each category using Large Language Models (LLMs) and employs adaptively learned textual templates to enhance the accuracy and interpretability of anomaly detection. HQ-Loc, utilizing Grounding DINO for preliminary localization, position-enhanced text prompts, and Multi-scale Multi-shape Cross-modal Interaction (MMCI) module, facilitates more accurate localization of anomalies of different sizes and shapes. Experimental results on datasets like MVTec and VisA demonstrate that FiLo significantly improves the performance of ZSAD in both detection and localization, achieving state-of-the-art performance with an image-level AUC of 83.9% and a pixel-level AUC of 95.9% on the VisA dataset. Code is available at https://github.com/CASIA-IVA-Lab/FiLo.
The main objective of this paper is to tackle visual localization, which is essential for the safe navigation of mobile robots. The solution we propose employs panoramic images and triplet convolutional neural networks. We seek to exploit the properties of such architectures to address both hierarchical and global localization in indoor environments, which are prone to visual aliasing and other phenomena. Considering their importance in these architectures, a complete comparative evaluation of different triplet loss functions is performed. The experimental section proves that triplet networks can be trained with a relatively low number of images captured under a specific lighting condition and even so, the resulting networks are a robust tool to perform visual localization under dynamic conditions. Our approach has been evaluated against some of these effects, such as changes in the lighting conditions, occlusions, noise and motion blurring. Furthermore, to explore the limits of our approach, triplet networks have been tested in different indoor environments simultaneously. In all the cases, these architectures have demonstrated a great capability to generalize to diverse and challenging scenarios. The code used in the experiments is available at https://github.com/MarcosAlfaro/TripletNetworksIndoorLocalization.git.
Generalizing to longer sentences is important for recent Transformer-based language models. Besides algorithms manipulating explicit position features, the success of Transformers without position encodings (NoPE) provides a new way to overcome the challenge. In this paper, we study the length generalization property of NoPE. We find that although NoPE can extend to longer sequences than the commonly used explicit position encodings, it still has a limited context length. We identify a connection between the failure of NoPE's generalization and the distraction of attention distributions. We propose a parameter-efficient tuning for searching attention heads' best temperature hyper-parameters, which substantially expands NoPE's context size. Experiments on long sequence language modeling, the synthetic passkey retrieval task and real-world long context tasks show that NoPE can achieve competitive performances with state-of-the-art length generalization algorithms. The source code is publicly accessible
Embedding models play a pivot role in modern NLP applications such as IR and RAG. While the context limit of LLMs has been pushed beyond 1 million tokens, embedding models are still confined to a narrow context window not exceeding 8k tokens, refrained from application scenarios requiring long inputs such as legal contracts. This paper explores context window extension of existing embedding models, pushing the limit to 32k without requiring additional training. First, we examine the performance of current embedding models for long context retrieval on our newly constructed LongEmbed benchmark. LongEmbed comprises two synthetic tasks and four carefully chosen real-world tasks, featuring documents of varying length and dispersed target information. Benchmarking results underscore huge room for improvement in these models. Based on this, comprehensive experiments show that training-free context window extension strategies like position interpolation can effectively extend the context window of existing embedding models by several folds, regardless of their original context being 512 or beyond 4k. Furthermore, for models employing absolute position encoding (APE), we show the possibility of further fine-tuning to harvest notable performance gains while strictly preserving original behavior for short inputs. For models using rotary position embedding (RoPE), significant enhancements are observed when employing RoPE-specific methods, such as NTK and SelfExtend, indicating RoPE's superiority over APE for context window extension. To facilitate future research, we release E5-Base-4k and E5-RoPE-Base, along with the LongEmbed benchmark.
Breathing monitoring is crucial in healthcare for early detection of health issues, but traditional methods face challenges like invasiveness, privacy concerns, and limited applicability in daily settings. This paper introduces light detection and ranging (LiDAR) sensors as a remote, privacy-respecting alternative for monitoring breathing metrics, including inhalation/exhalation patterns, respiratory rates, breath depth, and detecting breathlessness. We highlight LiDARs ability to function across various postures, presenting empirical evidence of its accuracy and reliability. Our findings position LiDAR as an innovative solution in breathing monitoring, offering significant advantages over conventional methods.
Large language models (LLMs) hold potential for innovative HCI research, including the creation of synthetic personae. However, their black-box nature and propensity for hallucinations pose challenges. To address these limitations, this position paper advocates for using LLMs as data augmentation systems rather than zero-shot generators. We further propose the development of robust cognitive and memory frameworks to guide LLM responses. Initial explorations suggest that data enrichment, episodic memory, and self-reflection techniques can improve the reliability of synthetic personae and open up new avenues for HCI research.
Building socially-intelligent AI agents (Social-AI) is a multidisciplinary, multimodal research goal that involves creating agents that can sense, perceive, reason about, learn from, and respond to affect, behavior, and cognition of other agents (human or artificial). Progress towards Social-AI has accelerated in the past decade across several computing communities, including natural language processing, machine learning, robotics, human-machine interaction, computer vision, and speech. Natural language processing, in particular, has been prominent in Social-AI research, as language plays a key role in constructing the social world. In this position paper, we identify a set of underlying technical challenges and open questions for researchers across computing communities to advance Social-AI. We anchor our discussion in the context of social intelligence concepts and prior progress in Social-AI research.
The performance of large language models (LLMs) is significantly influenced by the quality of the prompts provided. In response, researchers have developed enormous prompt engineering strategies aimed at modifying the prompt text to enhance task performance. In this paper, we introduce a novel technique termed position engineering, which offers a more efficient way to guide large language models. Unlike prompt engineering, which requires substantial effort to modify the text provided to LLMs, position engineering merely involves altering the positional information in the prompt without modifying the text itself. We have evaluated position engineering in two widely-used LLM scenarios: retrieval-augmented generation (RAG) and in-context learning (ICL). Our findings show that position engineering substantially improves upon the baseline in both cases. Position engineering thus represents a promising new strategy for exploiting the capabilities of large language models.
Virtual try-on and product personalization have become increasingly important in modern online shopping, highlighting the need for accurate body measurement estimation. Although previous research has advanced in estimating 3D body shapes from RGB images, the task is inherently ambiguous as the observed scale of human subjects in the images depends on two unknown factors: capture distance and body dimensions. This ambiguity is particularly pronounced in partial-view scenarios. To address this challenge, we propose a modular and simple height normalization solution. This solution relocates the subject skeleton to the desired position, thereby normalizing the scale and disentangling the relationship between the two variables. Our experimental results demonstrate that integrating this technique into state-of-the-art human mesh reconstruction models significantly enhances partial body measurement estimation. Additionally, we illustrate the applicability of this approach to multi-view settings, showcasing its versatility.
This paper argues that large language models have a valuable scientific role to play in serving as scientific models of a language. Linguistic study should not only be concerned with the cognitive processes behind linguistic competence, but also with language understood as an external, social entity. Once this is recognized, the value of large language models as scientific models becomes clear. This paper defends this position against a number of arguments to the effect that language models provide no linguistic insight. It also draws upon recent work in philosophy of science to show how large language models could serve as scientific models.