5 papers
YesTrack: Referring Multi-Object Tracking via MLLM-based Yes/No Verification
Quansheng Hu, Qin Sun, Qiansen Dai +4
Referring multi-object tracking (RMOT) aims to track every instance in a video that matches a given language expression. Despite the recent integration of multimodal large language…
OP4KSR: One-Step Patch-Free 4K Super-Resolution with Periodic Artifact Suppression
Chengyan Deng, Pengbin Yu, Zhentao Chen +6
Diffusion-based real-world image super-resolution (Real-ISR) has achieved remarkable perceptual quality; however, directly super-resolving images to 4K remains limited by extreme m…
Joint Geometric and Trajectory Consistency Learning for One-Step Real-World Super-Resolution
Chengyan Deng, Zhangquan Chen, Li Yu +3
Diffusion-based Real-World Image Super-Resolution (Real-ISR) achieves impressive perceptual quality but suffers from high computational costs due to iterative sampling. While recen…
GEA: Generation-Enhanced Alignment for Text-to-Image Person Retrieval
Hao Zou, Runqing Zhang, Xue Zhou +1
Text-to-Image Person Retrieval (TIPR) aims to retrieve person images based on natural language descriptions. Although many TIPR methods have achieved promising results, sometimes t…
AMNS: Attention-Weighted Selective Mask and Noise Label Suppression for Text-to-Image Person Retrieval
Runqing Zhang, Xue Zhou
Most existing text-to-image person retrieval methods usually assume that the training image-text pairs are perfectly aligned; however, the noisy correspondence(NC) issue (i.e., inc…