43 accepted papers
Reconstructing 3D human motion and human-object interactions (HOI) from Internet videos is a fundamental step toward building large-scale datasets of human behavior. Existing methods struggle to recover globally consistent 3D motion under dynamic cameras, especially for motion types underrepresented
We propose NEURONA, a modular neuro-symbolic framework for fMRI decoding and concept grounding in neural activity. Leveraging image- and video-based fMRI question-answering datasets, NEURONA learns to decode interacting concepts from visual stimuli from patterns of fMRI signals, integrating symbolic…
As the cost of pretraining large language models grows, there is continued interest in strategies to improve learning efficiency during this core training stage. Motivated by cognitive development, where humans gradually build knowledge as their brains mature, we propose Curriculum-Guided Layer Scal…
Diffusion Magnetic Resonance Imaging (dMRI) plays a critical role in studying microstructural changes in the brain. It is, therefore, widely used in clinical practice; yet progress in learning general-purpose representations from dMRI has been limited. A key challenge is that existing deep learning
Online 3D scene perception in real time is essential for robotics, AR/VR, and autonomous systems, particularly in edge computing scenarios where computational resources are limited and privacy is crucial. Recent state-of-the-art methods like EmbodiedSAM (ESAM) demonstrate the promise of online 3D pe
We present a feed-forward human performance capture method that renders novel views of a performer from a monocular RGB stream. A key challenge in this setting is the lack of sufficient observations, especially for unseen regions. Assuming the subject moves continuously over time, we take advantage…
Latent diffusion models excel at generating high-quality images but lose the benefits of end-to-end modeling. They discard information during image encoding, require a separately trained decoder, and model an auxiliary distribution to the raw data. In this paper, we propose Latent Forcing, a simple …
Understanding the physical world is essential for generalist AI agents. However, it remains unclear whether state-of-the-art vision perception models (e.g., large VLMs) can perform quantitative physical reasoning tasks. Existing evaluations are predominantly VQA-based and qualitative, offering limit
Lookup-free quantization has received much attention due to its efficiency on parameters and scalability to a large codebook. In this paper, we present a unified formulation of different non-parametric quantization methods through the lens of lattice coding. The geometry of lattice codes explains th
Human communication is inherently multimodal and social: words, prosody, and body language jointly carry intent. Yet most prior systems model human behavior as a translation task--co-speech gesture or text-to-motion that maps a fixed utterance to motion clips--without requiring agentic decision-maki
Confounders are extraneous variables that affect both the input and the target, resulting in spurious correlations and biased predictions. There are recent advances in dealing with or removing confounders in traditional models, such as metadata normalization (MDN), where the distribution of the lear…
Capturing diversity is crucial in conditional and prompt-based image generation, particularly when conditions contain uncertainty that can lead to multiple plausible outputs. To generate diverse images reflecting this diversity, traditional methods often modify random seeds, making it difficult to d…
In this paper, we present Latest Object Memory Management (LOMM) for temporally consistent video instance segmentation that significantly improves long-term instance tracking. At the core of our method is Latest Object Memory (LOM), which robustly tracks and continuously updates the latest states of…
Scaling by training on large datasets has been shown to enhance the quality and fidelity of image generation and manipulation with diffusion models; however, such large datasets are not always accessible in medical imaging due to cost and privacy issues, which contradicts one of the main application…
Efficient understanding of long-form videos remains a significant challenge in computer vision. In this work, we revisit temporal search paradigms for long-form video understanding, studying a fundamental issue pertaining to all state-of-the-art (SOTA) long-context vision-language models (VLMs). In…
Text-to-image diffusion models have seen significant development recently due to increasing availability of paired 2D data. Although a similar trend is emerging in 3D generation, the limited availability of high-quality 3D data has resulted in less competitive 3D diffusion models compared to their 2…
Human communication is inherently multimodal, involving a combination of verbal and non-verbal cues such as speech, facial expressions, and body gestures. Modeling these behaviors is essential for understanding human interaction and for creating virtual characters that can communicate naturally in a…
Egocentric human motion generation and forecasting with scene-context is crucial for enhancing AR/VR experiences, improving human-robot interaction, advancing assistive technologies, and enabling adaptive healthcare solutions by accurately predicting and simulating movement from a first-person persp…
Logical anomalies (LA) refer to data violating underlying logical constraints e.g., the quantity, arrangement, or composition of components within an image. Detecting accurately such anomalies requires models to reason about various component types through segmentation. However, curation of pixel-le…
This paper introduces a novel top-down representation approach for deformable image registration which estimates the deformation field by capturing various short- and long-range flow features at different scale levels. As a Hierarchical Vision Transformer (H-ViT) we propose a dual self-attention and…
Existing human rendering methods require every part of the human to be fully visible throughout the input video. However, this assumption does not hold in real-life settings where obstructions are common, resulting in only partial visibility of the human. Considering this, we present OccFusion, an a…
3D pose transfer that aims to transfer the desired pose to a target mesh is one of the most challenging 3D generation tasks. Previous attempts rely on well-defined parametric human models or skeletal joints as driving pose sources. However to obtain those clean pose sources cumbersome but necessary…
3D understanding and rendering of moving humans from monocular videos is a challenging task. Although recent progress has enabled this task to some extent, it is still difficult to guarantee satisfactory results in real-world scenarios, where obstacles may block the camera view and cause partial occ…
Video-language models (VLMs), large models pre-trained on numerous but noisy video-text pairs from the internet, have revolutionized activity recognition through their remarkable generalization and open-vocabulary capabilities. While complex human activities are often hierarchical and compositional,…
"The accelerated use of digital cameras prompts an increasing concern about privacy and security, particularly in applications such as action recognition. In this paper, we propose an optimizing framework to provide robust visual privacy protection along the human action recognition pipeline. Our fr…
Federated learning is an emerging research paradigm enabling collaborative training of machine learning models among different organizations while keeping data private at each institution. Despite recent progress, there remain fundamental challenges such as the lack of convergence and the potential…
While state-of-the-art 3D Convolutional Neural Networks (CNN) achieve very good results on action recognition datasets, they are computationally very expensive and require many GFLOPs. While the GFLOPs of a 3D CNN can be decreased by reducing the temporal feature resolution within the network, there…
Existing research on action recognition treats activities as monolithic events occurring in videos. Recently, the benefits of formulating actions as a combination of atomic-actions have shown promise in improving action understanding with the emergence of datasets containing such annotations, allowi…
Complex activities often involve multiple humans utilizing different objects to complete actions (e.g., in healthcare settings, physicians, nurses, and patients interact with each other and various medical devices). Recognizing activities poses a challenge that requires a detailed understanding of a…
Batch Normalization (BN) and its variants have delivered tremendous success in combating the covariate shift induced by the training step of deep learning methods. While these techniques normalize the feature distribution by standardizing with batch statistics, they do not correct the influence on f…
We propose a novel method for privacy-preserving training of deep neural networks leveraging public, out-domain data. While differential privacy (DP) has emerged as a mechanism to protect sensitive data in training datasets, its application to complex visual recognition tasks remains challenging. Tr…
Joint forecasting of human trajectory and pose dynamics is a fundamental building block of various applications ranging from robotics and autonomous driving to surveillance systems. Predicting body dynamics requires capturing subtle information embedded in the humans' interactions with each other an…
Human trajectory forecasting with multiple socially interact-ing agents is of critical importance for autonomous navigation in human environments, e.g., for self-driving cars and social robots. In this work, we present Predicted Endpoint Conditioned Network (PECNet) for flexible human trajectory pre…
In this paper, we study the problem of procedure planning in instructional videos, which can be seen as the first step towards enabling autonomous agents to plan for complex tasks in everyday settings such as cooking. Given the current visual observation of the world and a visual goal, we ask the qu…
Predicting the future is an important aspect for decision-making in robotics or autonomous driving systems, which heavily rely upon visual scene understanding. While prior work attempts to predict future video pixels, anticipate activities or forecast future scene semantic segments from segmentation
Smooth and seamless robot navigation while interacting with humans depends on predicting human movements. Forecasting such human dynamics often involves modeling human trajectories (global motion) or detailed body joint movements (local motion). Prior work typically tackled local and global human mo
Video captioning is a challenging task that requires a deep understanding of visual scenes. State-of-the-art methods generate captions using either scene-level or object-level information but without explicitly modeling object interactions. Thus, they often fail to make visually grounded predictions…
Reasoning over visual data is a desirable capability for robotics and vision-based applications. Such reasoning enables forecasting the next events or actions in videos. In recent years, various models have been developed based on convolution operations for prediction or forecasting, but they lack t
Modeling and prediction of human motion dynamics has long been a challenging problem in computer vision, and most existing methods rely on the end-to-end supervised training of various architectures of recurrent neural networks. Inspired by the recent success of deep reinforcement learning methods,…
In this paper, we propose a novel self-supervised representation learning by taking advantage of a neighborhood-relational encoding (NRE) among the training data. Conventional unsupervised learning methods only focused on training deep networks to understand the primitive characteristics of the visu…
Feature selection is one of the most important and widely-used dimension reduction techniques due to its efficiency and intractability of the results. In this paper, we propose a simple but efficient unsupervised feature ranking and selection method by exploiting the geometry of the original feature…
Novelty detection is the process of identifying the observation(s) that differ in some respect from the training observations (the target class). In reality, the novelty class is often absent during training, poorly sampled or not well defined. Therefore, one-class classifiers can efficiently model…
One of the main abilities that the robots need to maintain is to efficiently communicate with people in a humanly manner. Thus, human activity recognition (HAR) would be an integral part of such a human-robot interaction system. One of the major challenges in HAR is that the individuals perform thei…