T
Tongwei Ren
Researcher at Nanjing University
Publications - 92
Citations - 1851
Tongwei Ren is an academic researcher from Nanjing University. The author has contributed to research in topics: Computer science & Seam carving. The author has an hindex of 16, co-authored 84 publications receiving 1289 citations. Previous affiliations of Tongwei Ren include Hong Kong Polytechnic University & Nanjing University of Science and Technology.
Papers
More filters
Proceedings ArticleDOI
Depth saliency based on anisotropic center-surround difference
TL;DR: A novel saliency method that works on depth images based on anisotropic center-surround difference is proposed, which measures the saliency of a point by how much it outstands from surroundings, which takes the global depth structure into consideration.
Journal ArticleDOI
Depth-Aware Salient Object Detection and Segmentation via Multiscale Discriminative Saliency Fusion and Bootstrap Learning
TL;DR: A novel depth-aware salient object detection and segmentation framework via multiscale discriminative saliency fusion (MDSF) and bootstrap learning for RGBD images (RGB color images with corresponding Depth maps) and stereoscopic images achieves the better performance on both saliency detection and salient object segmentation.
Proceedings ArticleDOI
Salient object detection for RGB-D image via saliency evolution
Jingfan Quo,Tongwei Ren,Jia Bei +2 more
TL;DR: The proposed salient object detection method for RGB-D images based on evolution strategy outperforms the state-of-the-art methods and utilizes cellular automata to iteratively propagate saliency on the initial saliency map.
Journal ArticleDOI
Depth-aware salient object detection using anisotropic center-surround difference
TL;DR: The results compared with several state-of-the-art 2D and depth-aware methods show that the proposed saliency-based object segmentation method has the most satisfactory overall performance.
Proceedings ArticleDOI
Video Visual Relation Detection
TL;DR: A novel vision task named Video Visual Relation Detection (VidVRD) to perform visual relation detection in videos instead of still images (ImgVRD), which consists of object tracklet proposal, short-term relation prediction and greedy relational association is proposed.