Related papers: LSTA: Long Short-Term Attention for Egocentric Act…
The task of action detection aims at deducing both the action category and localization of the start and end moment for each action instance in a long, untrimmed video. While vision Transformers have driven the recent advances in video…
The goal of fine-grained action recognition is to successfully discriminate between action categories with subtle differences. To tackle this, we derive inspiration from the human visual system which contains specialized regions in the…
Advancements in egocentric video datasets like Ego4D, EPIC-Kitchens, and Ego-Exo4D have enriched the study of first-person human interactions, which is crucial for applications in augmented reality and assisted living. Despite these…
Egocentric vision captures the scene from the point of view of the camera wearer, while exocentric vision captures the overall scene context. Jointly modeling ego and exo views is crucial to developing next-generation AI agents. The…
With the increasing availability of wearable devices, research on egocentric activity recognition has received much attention recently. In this paper, we build a Multimodal Egocentric Activity dataset which includes egocentric videos and…
We introduce the Action Transformer model for recognizing and localizing human actions in video clips. We repurpose a Transformer-style architecture to aggregate features from the spatiotemporal context around the person whose actions we…
Action recognition in videos has attracted a lot of attention in the past decade. In order to learn robust models, previous methods usually assume videos are trimmed as short sequences and require ground-truth annotations of each video…
The recent trend in multiple object tracking (MOT) is heading towards leveraging deep learning to boost the tracking performance. In this paper, we propose a novel solution named TransSTAM, which leverages Transformer to effectively model…
Recent advances in egocentric video understanding models are promising, but their heavy computational expense is a barrier for many real-world applications. To address this challenge, we propose EgoDistill, a distillation-based approach…
Attention mechanisms have significantly boosted the performance of video classification neural networks thanks to the utilization of perspective contexts. However, the current research on video attention generally focuses on adopting a…
Understanding human activity is a crucial yet intricate task in egocentric vision, a field that focuses on capturing visual perspectives from the camera wearer's viewpoint. Traditional methods heavily rely on representation learning that is…
Training AI agents to proactively assist humans in daily activities, from routine household tasks to urgent safety situations, requires large-scale visual data. However, capturing such scenarios in the real world is often difficult, costly,…
In this paper we introduce a Transformer-based approach to video object segmentation (VOS). To address compounding error and scalability issues of prior work, we propose a scalable, end-to-end method for VOS called Sparse Spatiotemporal…
Class-agnostic object tracking is particularly difficult in cluttered environments as target specific discriminative models cannot be learned a priori. Inspired by how the human visual cortex employs spatial attention and separate "where"…
Spatiotemporal action recognition deals with locating and classifying actions in videos. Motivated by the latest state-of-the-art real-time object detector You Only Watch Once (YOWO), we aim to modify its structure to increase action…
Temporal object detection has attracted significant attention, but most popular detection methods cannot leverage rich temporal information in videos. Very recently, many algorithms have been developed for video detection task, yet very few…
Designing a technique for the automatic analysis of different actions in videos in order to detect the presence of interested activities is of high significance nowadays. In this paper, we explore a robust and dynamic appearance technique…
An integral part of video analysis and surveillance is temporal activity detection, which means to simultaneously recognize and localize activities in long untrimmed videos. Currently, the most effective methods of temporal activity…
We consider the problem of video-based person re-identification. The goal is to identify a person from videos captured under different cameras. In this paper, we propose an efficient spatial-temporal attention based model for person…
Scene understanding is central to general physical intelligence, and video is a primary modality for capturing both state and temporal dynamics of a scene. Yet understanding physical processes remains difficult, as models must combine…