Chung-Ching Lin

17

Papers

588

Total Citations

Papers (17)

Adaptive As-Natural-As-Possible Image Stitching

AR-Net: Adaptive Frame Resolution for Efficient Action Recognition

MM-Narrator: Narrating Long-form Videos with Multimodal In-Context Learning

SlowFast-VGen: Slow-Fast Learning for Action-Driven Long Video Generation

Point-RFT: Improving Multimodal Reasoning with Visually Grounded Reinforcement Finetuning

Cross-Modal Representation Learning for Zero-Shot Action Recognition

SwinBERT: End-to-End Transformers With Sparse Attention for Video Captioning

Adaptive Human Matting for Dynamic Videos

LAVENDER: Unifying Video-Language Understanding As Masked Language Modeling

Neural Voting Field for Camera-Space 3D Hand Pose Estimation

Equivariant Similarity for Vision-Language Foundation Models

Scaling Inference-Time Search with Vision Value Model for Improved Visual Comprehension

DisCo: Disentangled Control for Realistic Human Dance Generation

Completing Visual Objects via Bridging Generation and Segmentation

A Prior-Less Method for Multi-Face Tracking in Unconstrained Videos

Video Instance Segmentation Tracking With a Modified VAE Architecture

PaintSeg: Painting Pixels for Training-free Segmentation