Picture for Congqi Cao

Congqi Cao

Building a Multi-modal Spatiotemporal Expert for Zero-shot Action Recognition with CLIP

Add code
Dec 13, 2024
Viaarxiv icon

Task-Adapter: Task-specific Adaptation of Image Models for Few-shot Action Recognition

Add code
Aug 01, 2024
Viaarxiv icon

VS-TransGRU: A Novel Transformer-GRU-based Framework Enhanced by Visual-Semantic Fusion for Egocentric Action Anticipation

Add code
Jul 08, 2023
Viaarxiv icon

A New Comprehensive Benchmark for Semi-supervised Video Anomaly Detection and Anticipation

Add code
May 23, 2023
Figure 1 for A New Comprehensive Benchmark for Semi-supervised Video Anomaly Detection and Anticipation
Figure 2 for A New Comprehensive Benchmark for Semi-supervised Video Anomaly Detection and Anticipation
Figure 3 for A New Comprehensive Benchmark for Semi-supervised Video Anomaly Detection and Anticipation
Figure 4 for A New Comprehensive Benchmark for Semi-supervised Video Anomaly Detection and Anticipation
Viaarxiv icon

Co-Occurrence Matters: Learning Action Relation for Temporal Action Localization

Add code
Mar 15, 2023
Viaarxiv icon

Weakly Supervised Video Anomaly Detection Based on Cross-Batch Clustering Guidance

Add code
Dec 16, 2022
Viaarxiv icon

Context Recovery and Knowledge Retrieval: A Novel Two-Stream Framework for Video Anomaly Detection

Add code
Sep 07, 2022
Figure 1 for Context Recovery and Knowledge Retrieval: A Novel Two-Stream Framework for Video Anomaly Detection
Figure 2 for Context Recovery and Knowledge Retrieval: A Novel Two-Stream Framework for Video Anomaly Detection
Figure 3 for Context Recovery and Knowledge Retrieval: A Novel Two-Stream Framework for Video Anomaly Detection
Figure 4 for Context Recovery and Knowledge Retrieval: A Novel Two-Stream Framework for Video Anomaly Detection
Viaarxiv icon

Adaptive graph convolutional networks for weakly supervised anomaly detection in videos

Add code
Feb 14, 2022
Figure 1 for Adaptive graph convolutional networks for weakly supervised anomaly detection in videos
Figure 2 for Adaptive graph convolutional networks for weakly supervised anomaly detection in videos
Figure 3 for Adaptive graph convolutional networks for weakly supervised anomaly detection in videos
Figure 4 for Adaptive graph convolutional networks for weakly supervised anomaly detection in videos
Viaarxiv icon

Learnable Locality-Sensitive Hashing for Video Anomaly Detection

Add code
Nov 16, 2021
Figure 1 for Learnable Locality-Sensitive Hashing for Video Anomaly Detection
Figure 2 for Learnable Locality-Sensitive Hashing for Video Anomaly Detection
Figure 3 for Learnable Locality-Sensitive Hashing for Video Anomaly Detection
Figure 4 for Learnable Locality-Sensitive Hashing for Video Anomaly Detection
Viaarxiv icon

Efficient Spatialtemporal Context Modeling for Action Recognition

Add code
Apr 06, 2021
Figure 1 for Efficient Spatialtemporal Context Modeling for Action Recognition
Figure 2 for Efficient Spatialtemporal Context Modeling for Action Recognition
Figure 3 for Efficient Spatialtemporal Context Modeling for Action Recognition
Figure 4 for Efficient Spatialtemporal Context Modeling for Action Recognition
Viaarxiv icon