Related papers: Paxion: Patching Action Knowledge in Video-Languag…
We propose a function-based temporal pooling method that captures the latent structure of the video sequence data - e.g. how frame-level features evolve over time in a video. We show how the parameters of a function that has been fit to the…
The temporal action segmentation task segments videos temporally and predicts action labels for all frames. Fully supervising such a segmentation model requires dense frame-wise action annotations, which are expensive and tedious to…
Vision-Language-Action (VLA) models have recently achieved remarkable progress in robotic perception and control, yet most existing approaches primarily rely on VLM trained using 2D images, which limits their spatial understanding and…
The self-supervised pretraining paradigm has achieved great success in skeleton-based action recognition. However, these methods treat the motion and static parts equally, and lack an adaptive design for different parts, which has a…
Knowledge Tracing (KT) aims to predict learners' future performance from past interactions. While recent KT approaches have improved via learning item representations aligned with Knowledge Components, they overlook the procedural dynamics…
World models aim to learn action-controlled future prediction and have proven essential for the development of intelligent agents. However, most existing world models rely heavily on substantial action-labeled data and costly training,…
Many recent Vision-Language-Action models employ diffusion or flow-matching backbones with hundreds of millions of parameters for action generation. However, unlike image synthesis where the output spans millions of diverse pixels, a…
Action in video usually involves the interaction of human with objects. Action labels are typically composed of various combinations of verbs and nouns, but we may not have training data for all possible combinations. In this paper, we aim…
Understanding the progress of a task allows humans to not only track what has been done but also to better plan for future goals. We demonstrate TaKSIE, a novel framework that incorporates task progress knowledge into visual subgoal…
Understanding visual differences between dynamic scenes requires the comparative perception of compositional, spatial, and temporal changes--a capability that remains underexplored in existing vision-language systems. While prior work on…
Online action detection is a task with the aim of identifying ongoing actions from streaming videos without any side information or access to future frames. Recent methods proposed to aggregate fixed temporal ranges of invisible but…
With the rapid development of digital multimedia, video understanding has become an important field. For action recognition, temporal dimension plays an important role, and this is quite different from image recognition. In order to learn…
Vision-language models (VLMs) pre-trained on large-scale image-text pairs have demonstrated impressive transferability on various visual tasks. Transferring knowledge from such powerful VLMs is a promising direction for building effective…
Advanced driver assistance and automated driving systems rely on risk estimation modules to predict and avoid dangerous situations. Current methods use expensive sensor setups and complex processing pipeline, limiting their availability and…
Vision-language models are integral to computer vision research, yet many high-performing models remain closed-source, obscuring their data, design and training recipe. The research community has responded by using distillation from…
Gaze understanding unifies the detection of people, their gaze targets, and objects of interest into a single framework, offering critical insight into visual attention and intent estimation. Although prior research has modelled gaze cues…
A large amount of recent research has focused on tasks that combine language and vision, resulting in a proliferation of datasets and methods. One such task is action recognition, whose applications include image annotation, scene under-…
Action recognition is an open and challenging problem in computer vision. While current state-of-the-art models offer excellent recognition results, their computational expense limits their impact for many real-world applications. In this…
Automated surgical workflow analysis is crucial for education, research, and clinical decision-making, but the lack of annotated datasets hinders the development of accurate and comprehensive workflow analysis solutions. We introduce a…
In recent years, online lecture videos have become an increasingly popular resource for acquiring new knowledge. Systems capable of effectively understanding/indexing lecture videos are thus highly desirable, enabling downstream tasks like…