6 papers
Delayed Bidirectional Alignment via Disentangled Audio Semantics for Audio-Visual Segmentation
Jingqi Tian, Yiheng Du, Haoji Zhang +6
Audio-Visual Segmentation (AVS) aims to localize sound-producing objects at the pixel level by integrating auditory and visual cues. However, existing methods often struggle with m…
TAIHRI: Task-Aware 3D Human Keypoints Localization for Close-Range Human-Robot Interaction
Ao Li, Yonggen Ling, Yiyang Lin +3
Accurate 3D human keypoints localization is a critical technology enabling robots to achieve natural and safe physical interaction with users. Conventional 3D human keypoints estim…
Embed-RL: Reinforcement Learning for Reasoning-Driven Multimodal Embeddings
Haonan Jiang, Yuji Wang, Yongjie Zhu +5
Leveraging Multimodal Large Language Models (MLLMs) has become pivotal for advancing Universal Multimodal Embeddings (UME) in addressing diverse cross-modal tasks. Recent studies d…
VG-Refiner: Towards Tool-Refined Referring Grounded Reasoning via Agentic Reinforcement Learning
Yuji Wang, Wenlong Liu, Jingxuan Niu +2
Tool-integrated visual reasoning (TiVR) has demonstrated great potential in enhancing multimodal problem-solving. However, existing TiVR paradigms mainly focus on integrating vario…
SAM2-LOVE: Segment Anything Model 2 in Language-aided Audio-Visual Scenes
Yuji Wang, Haoran Xu, Yong Liu +2
Reference Audio-Visual Segmentation (Ref-AVS) aims to provide a pixel-wise scene understanding in Language-aided Audio-Visual Scenes (LAVS). This task requires the model to continu…
IteRPrimE: Zero-shot Referring Image Segmentation with Iterative Grad-CAM Refinement and Primary Word Emphasis
Yuji Wang, Jingchen Ni, Yong Liu +2
Zero-shot Referring Image Segmentation (RIS) identifies the instance mask that best aligns with a specified referring expression without training and fine-tuning, significantly red…