54 citations · 74 across the 17 of their papers we have counts for
19 papers · 1 filter
A Unified Score Matching Paradigm for Video Anomaly Detection and Anticipation
Congqi Cao, Zhenhe Liang, Hanwen Zhang +4
Video anomaly detection (VAD) is a fundamental and safety-critical task in computer vision. Recent generative approaches detect anomalies from a distributional perspective, but rem…
CueBench: Advancing Unified Understanding of Context-Aware Video Anomalies in Real-World
Yating Yu, Congqi Cao, Zhaoying Wang +6
How far are deep models from real-world video anomaly understanding (VAU)? Current works typically emphasize on detecting unexpected occurrences deviated from normal patterns or co…
Autoregressive Denoising Score Matching is a Good Video Anomaly Detector
Hanwen Zhang, Congqi Cao, Qinyi Lv +2
Video anomaly detection (VAD) is an important computer vision problem. Thanks to the mode coverage capabilities of generative models, the likelihood-based paradigm is catching grow…
Vision and Intention Boost Large Language Model in Long-Term Action Anticipation
Congqi Cao, Lanshu Hu, Yating Yu +1
Long-term action anticipation (LTA) aims to predict future actions over an extended period. Previous approaches primarily focus on learning exclusively from video data but lack pri…
Task-Adapter++: Task-specific Adaptation with Order-aware Alignment for Few-shot Action Recognition
Congqi Cao, Peiheng Han, Yueran zhang +4
Large-scale pre-trained models have achieved remarkable success in language and image tasks, leading an increasing number of studies to explore the application of pre-trained image…
Learning to Generalize without Bias for Open-Vocabulary Action Recognition
Yating Yu, Congqi Cao, Yifan Zhang +1
Leveraging the effective visual-text alignment and static generalizability from CLIP, recent video learners adopt CLIP initialization with further regularization or recombination f…
Building a Multi-modal Spatiotemporal Expert for Zero-shot Action Recognition with CLIP
Yating Yu, Congqi Cao, Yueran Zhang +3
Zero-shot action recognition (ZSAR) requires collaborative multi-modal spatiotemporal understanding. However, finetuning CLIP directly for ZSAR yields suboptimal performance, given…
Task-Adapter: Task-specific Adaptation of Image Models for Few-shot Action Recognition
Congqi Cao, Yueran Zhang, Yating Yu +3
Existing works in few-shot action recognition mostly fine-tune a pre-trained image model and design sophisticated temporal alignment modules at feature level. However, simply fully…
VS-TransGRU: A Novel Transformer-GRU-based Framework Enhanced by Visual-Semantic Fusion for Egocentric Action Anticipation
Congqi Cao, Ze Sun, Qinyi Lv +2
Egocentric action anticipation is a challenging task that aims to make advanced predictions of future actions from current and historical observations in the first-person view. Mos…
A New Comprehensive Benchmark for Semi-supervised Video Anomaly Detection and Anticipation
Congqi Cao, Yue Lu, Peng Wang +1
Semi-supervised video anomaly detection (VAD) is a critical task in the intelligent surveillance system. However, an essential type of anomaly in VAD named scene-dependent anomaly…
Co-Occurrence Matters: Learning Action Relation for Temporal Action Localization
Congqi Cao, Yizhe Wang, Yue Lu +2
Temporal action localization (TAL) is a prevailing task due to its great application potential. Existing works in this field mainly suffer from two weaknesses: (1) They often negle…
Weakly Supervised Video Anomaly Detection Based on Cross-Batch Clustering Guidance
Congqi Cao, Xin Zhang, Shizhou Zhang +2
Weakly supervised video anomaly detection (WSVAD) is a challenging task since only video-level labels are available for training. In previous studies, the discriminative power of t…
Context Recovery and Knowledge Retrieval: A Novel Two-Stream Framework for Video Anomaly Detection
Congqi Cao, Yue Lu, Yanning Zhang
Video anomaly detection aims to find the events in a video that do not conform to the expected behavior. The prevalent methods mainly detect anomalies by snippet reconstruction or…
Adaptive Graph Convolutional Networks for Weakly Supervised Anomaly Detection in Videos
Congqi Cao, Xin Zhang, Shizhou Zhang +2
For weakly supervised anomaly detection, most existing work is limited to the problem of inadequate video representation due to the inability of modeling long-term contextual infor…
Learnable Locality-Sensitive Hashing for Video Anomaly Detection
Yue Lu, Congqi Cao, Yanning Zhang
Video anomaly detection (VAD) mainly refers to identifying anomalous events that have not occurred in the training set where only normal samples are available. Existing works usual…
Efficient Spatialtemporal Context Modeling for Action Recognition
Congqi Cao, Yue Lu, Yifan Zhang +2
Contextual information plays an important role in action recognition. Local operations have difficulty to model the relation between two elements with a long-distance interval. How…
Few-shot Action Recognition with Implicit Temporal Alignment and Pair Similarity Optimization
Congqi Cao, Yajuan Li, Qinyi Lv +2
Few-shot learning aims to recognize instances from novel classes with few labeled samples, which has great value in research and application. Although there has been a lot of work…
Learning to Compare Relation: Semantic Alignment for Few-Shot Learning
Congqi Cao, Yanning Zhang
Few-shot learning is a fundamental and challenging problem since it requires recognizing novel categories from only a few examples. The objects for recognition have multiple varian…
Body Joint guided 3D Deep Convolutional Descriptors for Action Recognition
Congqi Cao, Yifan Zhang, Chunjie Zhang +1
Three dimensional convolutional neural networks (3D CNNs) have been established as a powerful tool to simultaneously learn features from both spatial and temporal dimensions, which…