An End-to-End Scene Text Detector with Dynamic Attention

TRL: Transformer based refinement learning for hybrid-supervised semantic segmentation

DPTNet: A Dual-Path Transformer Architecture for Scene Text Detection

Combating Noisy-Labeled and Imbalanced Data by Two Stage Bi-Dimensional Sample Selection

Learn-to-Decompose: Cascaded Decomposition Network for Cross-Domain Few-Shot Facial Expression Recognition

Stage-Aware Feature Alignment Network for Real-Time Semantic Segmentation of Street Scenes

When Sparse Neural Network Meets Label Noise Learning: A Multistage Learning Framework

When Facial Expression Recognition Meets Few-Shot Learning: A Joint and Alternate Learning Framework

Drop Loss for Person Attribute Recognition With Imbalanced Noisy-Labeled Samples

FastVOD-Net: A Real-Time and High-Accuracy Video Object Detector

FEDIC: FEDERATED LEARNING ON NON-IID AND LONG-TAILED DATA VIA CALIBRATED DISTILLATION

Federated Learning on Heterogeneous and Long-Tailed Data via Classifier Re-Training with Federated Features

Deep Multi-Branch Aggregation Network for Real-Time Semantic Segmentation in Street Scenes

Robust optical flow estimation to enhance behavioral research on ants

Adaptive Deep Disturbance-Disentangled Learning for Facial Expression Recognition

Optical flow estimation via weighted guided filtering with non-local steering kernel

TSGB: Target-Selective Gradient Backprop for Probing CNN Visual Saliency

Triplet Relationship Guided Sampling Consensus for Robust Model Estimation

MULTI-FOCUS GUIDED SEMANTIC AGGREGATION FOR VIDEO OBJECT DETECTION

LEARNING CORRELATION FOR ONLINE MULTIPLE OBJECT TRACKING

BOUNDING BOX DISTRIBUTION LEARNING AND CENTER POINT CALIBRATION FOR ROBUST VISUAL TRACKING

Dual Selection Network for Video Object Detection

Siamese Template Diffusion Networks for Robust Visual Tracking

FEDIC: Federated Learning on Non-IID and Long-Tailed Data via Calibrated Distillation

Co-Clustering on Bipartite Graphs for Robust Model Fitting

Embedding Adaptation Network with Transformer for Few-Shot Action Recognition

A NEW FRAMEWORK FOR MULTIPLE DEEP CORRELATION FILTERS BASED OBJECT TRACKING

Learn-to-Decompose: Cascaded Decomposition Network for Cross-Domain Few-Shot Facial Expression Recognition

DUALFEAT: DUAL FEATURE AGGREGATION FOR VIDEO OBJECT DETECTION

VISUAL TEMPO CONTRASTIVE LEARNING FOR FEW-SHOT ACTION RECOGNITION

GUIDED SAMPLING BASED FEATURE AGGREGATION FOR VIDEO OBJECT DETECTION

MDNET: MOTION DISTINCTION NETWORK FOR EFFECTIVE ACTION RECOGNITION

EGNET: A NOVEL EDGE GUIDED NETWORK FOR INSTANCE SEGMENTATION

SCINET: SEMANTIC CUE INFUSION NETWORK FOR LANE DETECTION

MSFL-Net: Multi-Semantic Feature Learning Network for Occluded Person Re-Identification