Related papers: E2E-LOAD: End-to-End Long-form Online Action Detec…

Most current pipelines for spatio-temporal action localization connect frame-wise or clip-wise detection results to generate action proposals, where only local information is exploited and the efficiency is hindered by dense per-frame…

Online action detection (OAD) aims to identify ongoing actions from streaming video in real-time, without access to future frames. Since these actions manifest at varying scales of granularity, ranging from coarse to fine, projecting an…

Cooperative inference in Mobile Edge Computing (MEC), achieved by deploying partitioned Deep Neural Network (DNN) models between resource-constrained user equipments (UEs) and edge servers (ESs), has emerged as a promising paradigm.…

Temporal action detection (TAD) aims to determine the semantic label and the temporal interval of every action instance in an untrimmed video. It is a fundamental and challenging task in video understanding. Previous methods tackle this…

Detecting actions as they occur is essential for applications like video surveillance, autonomous driving, and human-robot interaction. Known as online action detection, this task requires classifying actions in streaming videos, handling…

Existing end-to-end Multi-Object Tracking (e2e-MOT) methods have not surpassed non-end-to-end tracking-by-detection methods. One potential reason is its label assignment strategy during training that consistently binds the tracked objects…

Temporal action detection (TAD) aims to detect the semantic labels and boundaries of action instances in untrimmed videos. Current mainstream approaches are multi-step solutions, which fall short in efficiency and flexibility. In this…

Traditional security detection methods face three key challenges: inadequate data collection that misses critical security events, resource-intensive monitoring systems, and poor detection algorithms with high false positive rates. We…

The problem of Online Human Behaviour Recognition in untrimmed videos, aka Online Action Detection (OAD), needs to be revisited. Unlike traditional offline action detection approaches, where the evaluation metrics are clear and well…

End-to-end (E2E) models have shown to outperform state-of-the-art conventional models for streaming speech recognition [1] across many dimensions, including quality (as measured by word error rate (WER)) and endpointer latency [2]. However,…

A principal barrier to large-scale deployment of urban autonomous driving systems lies in the prevalence of complex scenarios and edge cases. Existing systems fail to effectively interpret semantic information within traffic contexts and…

Edge intelligence (EI) allows resource-constrained edge devices (EDs) to offload computation-intensive AI tasks (e.g., visual object detection) to edge servers (ESs) for fast execution. However, transmitting high-volume raw task data (e.g.,…

We propose a novel neural network-based end-to-end acoustic echo cancellation (E2E-AEC) method capable of streaming inference, which operates effectively without reliance on traditional linear AEC (LAEC) techniques and time delay…

Large reasoning models, such as OpenAI o1 and DeepSeek-R1, tend to become increasingly verbose as their reasoning capabilities improve. These inflated Chain-of-Thought (CoT) trajectories often exceed what the underlying problems require,…

Although end-to-end (E2E) learning has led to impressive progress on a variety of visual understanding tasks, it is often impeded by hardware constraints (e.g., GPU memory) and is prone to overfitting. When it comes to video captioning, one…

Anomaly detection (AD) identifies the defect regions of a given image. Recent works have studied AD, focusing on learning AD without abnormal images, with long-tailed distributed training data, and using a unified model for all classes. In…

Online learning is an important technical means for sketching massive real-time and high-speed data. Although this direction has attracted intensive attention, most of the literature in this area ignore the following three issues: (1) they…

Complex physical simulations often require trade-offs between model fidelity and computational feasibility. We introduce Adaptive Online Emulation (AOE), which dynamically learns neural network surrogates during simulation execution to…

Temporal Action Detection (TAD) is an essential and challenging topic in video understanding, aiming to localize the temporal segments containing human action instances and predict the action categories. The previous works greatly rely upon…

For realizing safe autonomous driving, the end-to-end delays of real-time object detection systems should be thoroughly analyzed and minimized. However, despite recent development of neural networks with minimized inference delays,…