Related papers: Guided Attention for Next Active Object @ EGO4D ST…
In this report, we present our champion solutions to five tracks at Ego4D challenge. We leverage our developed InternVideo, a video foundation model, for five Ego4D tasks, including Moment Queries, Natural Language Queries, Future Hand…
Deep neural networks, especially transformer-based architectures, have achieved remarkable success in semantic segmentation for environmental perception. However, existing models process video frames independently, thus failing to leverage…
Accurately detecting student behavior from classroom videos is beneficial for analyzing their classroom status and improving teaching efficiency. However, low accuracy in student classroom behavior detection is a prevalent issue. To address…
Self-attention learns pairwise interactions to model long-range dependencies, yielding great improvements for video action recognition. In this paper, we seek a deeper understanding of self-attention for temporal modeling in videos. We…
Video Instance Segmentation is a fundamental computer vision task that deals with segmenting and tracking object instances across a video sequence. Most existing methods typically accomplish this task by employing a multi-stage top-down…
This paper addresses the problem of anticipating the next-active-object location in the future, for a given egocentric video clip where the contact might happen, before any action takes place. The problem is considerably hard, as we aim at…
This paper studies the computational offloading of video action recognition in edge computing. To achieve effective semantic information extraction and compression, following semantic communication we propose a novel spatiotemporal…
The next location recommendation is at the core of various location-based applications. Current state-of-the-art models have attempted to solve spatial sparsity with hierarchical gridding and model temporal relation with explicit time…
Video action detection (spatio-temporal action localization) is usually the starting point for human-centric intelligent analysis of videos nowadays. It has high practical impacts for many applications across robotics, security, healthcare,…
First-person action recognition is a challenging task in video understanding. Because of strong ego-motion and a limited field of view, many backgrounds or noisy frames in a first-person video can distract an action recognition model during…
We propose a Dynamic Graph-Based Spatial-Temporal Attention (DG-STA) method for hand gesture recognition. The key idea is to first construct a fully-connected graph from a hand skeleton, where the node features and edges are then…
Attention mechanisms have made significant strides in graph learning, yet they still exhibit notable limitations: local attention faces challenges in capturing long-range information due to the inherent problems of the message-passing…
Video prediction aims to predict future frames by modeling the complex spatiotemporal dynamics in videos. However, most of the existing methods only model the temporal information and the spatial information for videos in an independent…
Pre-trained vision-language models provide a robust foundation for efficient transfer learning across various downstream tasks. In the field of video action recognition, mainstream approaches often introduce additional modules to capture…
With the rising focus on quadrupeds, a generalized policy capable of handling different robot models and sensor inputs becomes highly beneficial. Although several methods have been proposed to address different morphologies, it remains a…
In this paper, we address the challenge of understanding human activities from an egocentric perspective. Traditional activity recognition techniques face unique challenges in egocentric videos due to the highly dynamic nature of the head…
The ubiquitous multi-camera setup on modern autonomous vehicles provides an opportunity to construct surround-view depth. Existing methods, however, either perform independent monocular depth estimations on each camera or rely on…
In egocentric scenarios, anticipating both the next action and its visual outcome is essential for understanding human-object interactions and for enabling robotic planning. However, existing paradigms fall short of jointly modeling these…
Deep robot vision models are widely used for recognizing objects from camera images, but shows poor performance when detecting objects at untrained positions. Although such problem can be alleviated by training with large datasets, the…
Understanding the movement patterns of objects (e.g., humans and vehicles) in a city is essential for many applications, including city planning and management. This paper proposes a method for predicting future city-wide crowd flows by…