Fangyun Wei

36

Papers

258

Total Citations

Papers (36)

Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimation

EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test

Hybrid Proposal Refiner: Revisiting DETR Series from the Faster R-CNN Perspective

Beyond Text: Frozen Large Language Models in Visual Signal Comprehension

AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls

Rethinking Generative Large Language Model Evaluation for Semantic Comprehension

EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty

Group Sampling for Scale Invariant Face Detection

High-Fidelity and Arbitrary Face Editing

A Simple Multi-Modality Transfer Learning Baseline for Sign Language Translation

Learning To Prompt for Open-Vocabulary Object Detection With Vision-Language Model

Frame-Wise Action Representations for Long Videos via Sequence Contrastive Learning

Cross-Model Pseudo-Labeling for Semi-Supervised Action Recognition

TinyMIM: An Empirical Study of Distilling MIM Pre-Trained Models

Iterative Proposal Refinement for Weakly-Supervised Video Grounding

Natural Language-Assisted Sign Language Recognition

Side Adapter Network for Open-Vocabulary Semantic Segmentation

CiCo: Domain-Aware Sign Language Retrieval via Cross-Lingual Contrastive Learning

Two-Shot Video Object Segmentation

End-to-End Semi-Supervised Object Detection With Soft Teacher

ADNet: Leveraging Error-Bias Towards Normal Direction in Face Alignment

Dual Path Learning for Domain Adaptation of Semantic Segmentation

Attentive Mask CLIP

Improving Continuous Sign Language Recognition with Cross-Lingual Signs

Design and Interpretation of Universal Adversarial Patches in Face Detection

A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-Language Model

Minimizing Labeled, Maximizing Unlabeled: An Image-Driven Approach for Video Instance Segmentation

UniGraspTransformer: Simplified Policy Distillation for Scalable Dexterous Robotic Grasping

Improved Noise Schedule for Diffusion Training

Restoring Negative Information in Few-Shot Object Detection

RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder

Bootstrap Your Object Detector via Mixed Training

Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning

Aligning Pretraining for Detection via Object-Level Contrastive Learning

Two-Stream Network for Sign Language Recognition and Translation

AniFaceGAN: Animatable 3D-Aware Face Image Generation for Video Avatars