401 citations · 850 across the 15 of their papers we have counts for
4 papers · 1 filter
Towards Video Anomaly Retrieval from Video Anomaly Detection: New Benchmarks and Model
Peng Wu, Jing Liu, Xiangteng He +3
Video anomaly detection (VAD) has been paid increasing attention due to its potential applications, its current dominant tasks focus on online detecting anomalies% at the frame lev…
PosterLayout: A New Benchmark and Approach for Content-aware Visual-Textual Presentation Layout
HsiaoYuan Hsu, Xiangteng He, Yuxin Peng +2
Content-aware visual-textual presentation layout aims at arranging spatial space on the given canvas for pre-defined elements, including text, logo, and underlay, which is a key to…
Scanning Only Once: An End-to-end Framework for Fast Temporal Grounding in Long Videos
Yulin Pan, Xiangteng He, Biao Gong +4
Video temporal grounding aims to pinpoint a video segment that matches the query description. Despite the recent advance in short-form videos (\textit{e.g.}, in minutes), temporal…
Enhancing Unsupervised Audio Representation Learning via Adversarial Sample Generation
Yulin Pan, Xiangteng He, Biao Gong +2
Existing audio analysis methods generally first transform the audio stream to spectrogram, and then feed it into CNN for further analysis. A standard CNN recognizes specific visual…