Related papers: E2E-LOAD: End-to-End Long-form Online Action Detec…
The remarkable success of pretrain-then-finetune paradigm has led to a proliferation of available pre-trained models for vision tasks. This surge presents a significant challenge in efficiently choosing the most suitable pre-trained models…
Online adaptive model reduction efficiently reduces numerical models of transport-dominated problems by updating reduced spaces over time, which leads to nonlinear approximations on latent manifolds that can achieve a faster error decay…
In an era marked by the rapid scaling of foundation models, autonomous driving technologies are approaching a transformative threshold where end-to-end autonomous driving (E2E-AD) emerges due to its potential of scaling up in the…
Multilingual end-to-end (E2E) models have shown great promise in expansion of automatic speech recognition (ASR) coverage of the world's languages. They have shown improvement over monolingual systems, and have simplified training and…
Temporal Action Detection(TAD) is a crucial but challenging task in video understanding.It is aimed at detecting both the type and start-end frame for each action instance in a long, untrimmed video.Most current models adopt both RGB and…
Successful machine learning involves a complete pipeline of data, model, and downstream applications. Instead of treating them separately, there has been a prominent increase of attention within the constrained optimization (CO) and machine…
Streaming video clips with large-scale video tokens impede vision transformers (ViTs) for efficient recognition, especially in video action detection where sufficient spatiotemporal representations are required for precise actor…
The state of the art in video understanding suffers from two problems: (1) The major part of reasoning is performed locally in the video, therefore, it misses important relationships within actions that span several seconds. (2) While there…
Anomaly detection in decision-making sequences is a challenging problem due to the complexity of normality representation learning and the sequential nature of the task. Most existing methods based on Reinforcement Learning (RL) are…
Although numerous recent tracking approaches have made tremendous advances in the last decade, achieving high-performance visual tracking remains a challenge. In this paper, we propose an end-to-end network model to learn reinforced…
In recent years, deep network-based methods have continuously refreshed state-of-the-art performance on Salient Object Detection (SOD) task. However, the performance discrepancy caused by different implementation details may conceal the…
End-to-end autonomous driving (E2E-AD) has emerged as a promising paradigm that unifies perception, prediction, and planning into a holistic, data-driven framework. However, achieving robustness to varying camera viewpoints, a common…
The attention mechanism provides a sequential prediction framework for learning spatial models with enhanced implicit temporal consistency. In this work, we show a systematic design (from 2D to 3D) for how conventional networks and other…
Video Anomaly Detection (VAD) identifies unusual activities in video streams, a key technology with broad applications ranging from surveillance to healthcare. Tackling VAD in real-life settings poses significant challenges due to the…
Long-term user behavior sequences are a goldmine for businesses to explore users' interests to improve Click-Through Rate. However, it is very challenging to accurately capture users' long-term interests from their long-term behavior…
Motion style transfer is a common method for enriching character animation. Motion style transfer algorithms are often designed for offline settings where motions are processed in segments. However, for online animation applications, such…
Real-time video analytics on the edge is challenging as the computationally constrained resources typically cannot analyse video streams at full fidelity and frame rate, which results in loss of accuracy. This paper proposes a Transprecise…
Efficient and effective Out-of-Distribution (OOD) detection is essential for the safe deployment of AI systems. Existing feature space methods, while effective, often incur significant computational overhead due to their reliance on…
Temporal Action Detection (TAD) aims to identify and localize actions by determining their starting and ending frames within untrimmed videos. Recent Structured State-Space Models such as Mamba have demonstrated potential in TAD due to…
Pedestrian dead reckoning is a challenging task due to the low-cost inertial sensor error accumulation. Recent research has shown that deep learning methods can achieve impressive performance in handling this issue. In this letter, we…