43 citations · 127 across the 8 of their papers we have counts for
9 papers
VideoSlate: Stateful Commit Control for Temporally Grounded Agentic Video Reasoning
Shuo Zheng, Yuanjie Dang, Peng Chen +4
Agentic video reasoning systems gather and assess video evidence across stages, selecting relevant spans as visual evidence for answering questions. New candidates and observations…
Towards Robust Multimodal Emotion Recognition under Missing Modalities and Distribution Shifts
Guowei Zhong, Ruohong Huan, Mingzhen Wu +2
Recent advancements in Multimodal Emotion Recognition (MER) face challenges in addressing both modality missing and Out-Of-Distribution (OOD) data simultaneously. Existing methods…
AFPN: Asymptotic Feature Pyramid Network for Object Detection
Guoyu Yang, Jie Lei, Zhikuan Zhu +3
Multi-scale features are of great importance in encoding objects with scale variance in object detection tasks. A common strategy for multi-scale feature extraction is adopting the…
Internal Structure Attention Network for Fingerprint Presentation Attack Detection from Optical Coherence Tomography
Haohao Sun, Yilong Zhang, Peng Chen +2
As a non-invasive optical imaging technique, optical coherence tomography (OCT) has proven promising for automatic fingerprint recognition system (AFRS) applications. Diverse appro…
A Visual Representation-guided Framework with Global Affinity for Weakly Supervised Salient Object Detection
Binwei Xu, Haoran Liang, Weihua Gong +2
Fully supervised salient object detection (SOD) methods have made considerable progress in performance, yet these models rely heavily on expensive pixel-wise labels. Recently, to a…
Synthesize Boundaries: A Boundary-aware Self-consistent Framework for Weakly Supervised Salient Object Detection
Binwei Xu, Haoran Liang, Ronghua Liang +1
Fully supervised salient object detection (SOD) has made considerable progress based on expensive and time-consuming data with pixel-wise annotations. Recently, to relieve the labe…
Motion-aware Memory Network for Fast Video Salient Object Detection
Xing Zhao, Haoran Liang, Peipei Li +4
Previous methods based on 3DCNN, convLSTM, or optical flow have achieved great success in video salient object detection (VSOD). However, they still suffer from high computational…
Learning Video Salient Object Detection Progressively from Unlabeled Videos
Binwei Xu, Haoran Liang, Wentian Ni +3
Recent deep learning-based video salient object detection (VSOD) has achieved some breakthrough, but these methods rely on expensive annotated videos with pixel-wise annotations, w…
3D Instance Segmentation of MVS Buildings
Jiazhou Chen, Yanghui Xu, Shufang Lu +2
We present a novel 3D instance segmentation framework for Multi-View Stereo (MVS) buildings in urban scenes. Unlike existing works focusing on semantic segmentation of urban scenes…