Imaging and video networks

Synthetic Pseudo Anomalies for Unsupervised Video Anomaly Detection: A Simple yet Efficient Framework based on Masked Autoencoder

A Video Anomaly Detection Framework based on Appearance-Motion Semantics Representation Consistency

REPETITION COUNTING FROM COMPRESSED VIDEOS USING SPARSE RESIDUAL SIMILARITY

SELF-SIMILARITY IS ALL YOU NEED FOR FAST AND LIGHT-WEIGHT GENERIC EVENT BOUNDARY DETECTION

DMFormer: Closing the Gap between CNN and Vision Transformers

Enhanced DCF Tracker Regularized by Reliable Sample Construction

LEARNING A WEIGHT MAP FOR WEAKLY-SUPERVISED LOCALIZATION

Random Projector: Efficient Deep Image Prior

CFFMixer: Multi-dimensional Feature Fusion For Object Detection

CORSD: Class-Oriented Relational Self Distillation

STRUCTURE-PRESERVING AND REDUNDANCY-FREE FEATURES REFINEMENT FOR GENERALIZED ZERO-SHOT LEARNING

Solving Jigsaw Puzzle of Large Eroded Gaps Using Puzzlet Discriminant Network