most citedAIM 2024 Challenge on Video Saliency Prediction: Methods and Results

8 citations · 10 across the 14 of their papers we have counts for

collaborators
Showing cs.CVShow all

14 papers · 1 filter

cs.CV2025

Towards Ancient Plant Seed Classification: A Benchmark Dataset and Baseline Model

Rui Xing, Runmin Cong, Yingying Wu +5

Understanding the dietary preferences of ancient societies and their evolution across periods and regions is crucial for revealing human-environment interactions. Seeds, as importa…

cs.CV2025

SAM-DAQ: Segment Anything Model with Depth-guided Adaptive Queries for RGB-D Video Salient Object Detection

Jia Lin, Xiaofei Zhou, Jiyuan Liu +4

Recently segment anything model (SAM) has attracted widespread concerns, and it is often treated as a vision foundation model for universal segmentation. Some researchers have atte…

cs.CV2025

Empowering DINO Representations for Underwater Instance Segmentation via Aligner and Prompter

Zhiyang Chen, Chen Zhang, Hao Fang +1

Underwater instance segmentation (UIS), integrating pixel-level understanding and instance-level discrimination, is a pivotal technology in marine resource exploration and ecologic…

cs.CV2025

Semantic Concentration for Self-Supervised Dense Representations Learning

Peisong Wen, Qianqian Xu, Siran Dai +2

Recent advances in image-level self-supervised learning (SSL) have made significant progress, yet learning dense representations for patches remains challenging. Mainstream methods…

cs.CV20251 cited

UIS-Mamba: Exploring Mamba for Underwater Instance Segmentation via Dynamic Tree Scan and Hidden State Weaken

Runmin Cong, Zongji Yu, Hao Fang +2

Underwater Instance Segmentation (UIS) tasks are crucial for underwater complex scene detection. Mamba, as an emerging state space model with inherently linear complexity and globa…

cs.CV2025

Stereo-GS: Multi-View Stereo Vision Model for Generalizable 3D Gaussian Splatting Reconstruction

Xiufeng Huang, Ka Chun Cheung, Runmin Cong +2

Generalizable 3D Gaussian Splatting reconstruction showcases advanced Image-to-3D content creation but requires substantial computational resources and large datasets, posing chall…