9 citations · 29 across the 38 of their papers we have counts for
14 papers · 1 filter
WaterWave: Bridging Underwater Image Enhancement into Video Streams via Wavelet-based Temporal Consistency Field
Qi Zhu, Jingyi Zhang, Naishan Zheng +4
Underwater video pairs are fairly difficult to obtain due to the complex underwater imaging. In this case, most existing video underwater enhancement methods are performed by direc…
SAM3-Adapter: Efficient Adaptation of Segment Anything 3 for Camouflage Object Segmentation, Shadow Detection, and Medical Image Segmentation
Tianrun Chen, Runlong Cao, Xinda Yu +8
The rapid rise of large-scale foundation models has reshaped the landscape of image segmentation, with models such as Segment Anything achieving unprecedented versatility across di…
RAVEN++: Pinpointing Fine-Grained Violations in Advertisement Videos with Active Reinforcement Reasoning
Deyi Ji, Yuekui Yang, Liqun Liu +7
Advertising (Ad) is a cornerstone of the digital economy, yet the moderation of video advertisements remains a significant challenge due to their complexity and the need for precis…
Multi-Agent VLMs Guided Self-Training with PNU Loss for Low-Resource Offensive Content Detection
Han Wang, Deyi Ji, Junyu Lu +6
Accurate detection of offensive content on social media demands high-quality labeled data; however, such data is often scarce due to the low prevalence of offensive instances and t…
Retrv-R1: A Reasoning-Driven MLLM Framework for Universal and Efficient Multimodal Retrieval
Lanyun Zhu, Deyi Ji, Tianrun Chen +2
The success of DeepSeek-R1 demonstrates the immense potential of using reinforcement learning (RL) to enhance LLMs' reasoning capabilities. This paper introduces Retrv-R1, the firs…
RAVEN: Robust Advertisement Video Violation Temporal Grounding via Reinforcement Reasoning
Deyi Ji, Yuekui Yang, Haiyang Wu +3
Advertisement (Ad) video violation detection is critical for ensuring platform compliance, but existing methods struggle with precise temporal grounding, noisy annotations, and lim…
Self-signals Driven Multi-LLM Debate for Efficient and Accurate Reasoning
Xuhang Chen, Zhifan Song, Deyi Ji +2
Large Language Models (LLMs) have exhibited impressive capabilities across diverse application domains. Recent work has explored Multi-LLM Agent Debate (MAD) as a way to enhance pe…
From Air to Wear: Personalized 3D Digital Fashion with AR/VR Immersive 3D Sketching
Ying Zang, Yuanqi Hu, Xinyu Chen +7
In the era of immersive consumer electronics, such as AR/VR headsets and smart devices, people increasingly seek ways to express their identity through virtual fashion. However, ex…
POPEN: Preference-Based Optimization and Ensemble for LVLM-Based Reasoning Segmentation
Lanyun Zhu, Tianrun Chen, Qianxiong Xu +5
Existing LVLM-based reasoning segmentation methods often suffer from imprecise segmentation results and hallucinations in their text responses. This paper introduces POPEN, a novel…
Structural and Statistical Texture Knowledge Distillation and Learning for Segmentation
Deyi Ji, Feng Zhao, Hongtao Lu +2
Low-level texture feature/knowledge is also of vital importance for characterizing the local structural pattern and global statistical properties, such as boundary, smoothness, reg…
Breaking the Box: Enhancing Remote Sensing Image Segmentation with Freehand Sketches
Ying Zang, Yuncan Gao, Jiangi Zhang +7
This work advances zero-shot interactive segmentation for remote sensing imagery through three key contributions. First, we propose a novel sketch-based prompting method, enabling…
Let Human Sketches Help: Empowering Challenging Image Segmentation Task with Freehand Sketches
Ying Zang, Runlong Cao, Jianqi Zhang +8
Sketches, with their expressive potential, allow humans to convey the essence of an object through even a rough contour. For the first time, we harness this expressive potential to…
Not Every Patch is Needed: Towards a More Efficient and Effective Backbone for Video-based Person Re-identification
Lanyun Zhu, Tianrun Chen, Deyi Ji +2
This paper proposes a new effective and efficient plug-and-play backbone for video-based person re-identification (ReID). Conventional video-based ReID methods typically use CNN or…
Generating Negative Samples for Multi-Modal Recommendation
Yanbiao Ji, Dan Luo, Chang Liu +6
Multi-modal recommender systems (MMRS) have gained significant attention due to their ability to leverage information from various modalities to enhance recommendation quality. How…