8 citations · 31 across the 40 of their papers we have counts for
15 papers · 1 filter
Structural Pruning via Spatial-aware Information Redundancy for Semantic Segmentation
Dongyue Wu, Zilin Guo, Li Yu +2
In recent years, semantic segmentation has flourished in various applications. However, the high computational cost remains a significant challenge that hinders its further adoptio…
Adaptive Prototype Replay for Class Incremental Semantic Segmentation
Guilin Zhu, Dongyue Wu, Changxin Gao +3
Class incremental semantic segmentation (CISS) aims to segment new classes during continual steps while preventing the forgetting of old knowledge. Existing methods alleviate catas…
Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity
Huaxin Zhang, Xiaohao Xu, Xiang Wang +6
How can we enable models to comprehend video anomalies occurring over varying temporal scales and contexts? Traditional Video Anomaly Understanding (VAU) methods focus on frame-lev…
Improving Multi-modal Large Language Model through Boosting Vision Capabilities
Yanpeng Sun, Huaxin Zhang, Qiang Chen +5
We focus on improving the visual understanding capability for boosting the vision-language models. We propose \textbf{Arcana}, a multiModal language model, which introduces two cru…
DFIMat: Decoupled Flexible Interactive Matting in Multi-Person Scenarios
Siyi Jiao, Wenzheng Zeng, Changxin Gao +1
Interactive portrait matting refers to extracting the soft portrait from a given image that best meets the user's intent through their inputs. Existing methods often underperform i…
Cross-video Identity Correlating for Person Re-identification Pre-training
Jialong Zuo, Ying Nie, Hanyu Zhou +5
Recent researches have proven that pre-training on large-scale person images extracted from internet videos is an effective way in learning better representations for person re-ide…
Replace Anyone in Videos
Xiang Wang, Shiwei Zhang, Haonan Qiu +7
The field of controllable human-centric video generation has witnessed remarkable progress, particularly with the advent of diffusion models. However, achieving precise and localiz…
Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLM
Huaxin Zhang, Xiaohao Xu, Xiang Wang +6
Towards open-ended Video Anomaly Detection (VAD), existing methods often exhibit biased detection when faced with challenging or unseen events and lack interpretability. To address…
Open-Vocabulary Semantic Segmentation with Image Embedding Balancing
Xiangheng Shan, Dongyue Wu, Guilin Zhu +3
Open-vocabulary semantic segmentation is a challenging task, which requires the model to output semantic masks of an image beyond a close-set vocabulary. Although many efforts have…
UniAnimate: Taming Unified Video Diffusion Models for Consistent Human Image Animation
Xiang Wang, Shiwei Zhang, Changxin Gao +5
Recent diffusion-based human image animation techniques have demonstrated impressive success in synthesizing videos that faithfully follow a given reference identity and a sequence…
Tunnel Try-on: Excavating Spatial-temporal Tunnels for High-quality Virtual Try-on in Videos
Zhengze Xu, Mengting Chen, Zhao Wang +6
Video try-on is a challenging task and has not been well tackled in previous works. The main obstacle lies in preserving the details of the clothing and modeling the coherent motio…
REPAIR: Rank Correlation and Noisy Pair Half-replacing with Memory for Noisy Correspondence
Ruochen Zheng, Jiahao Hong, Changxin Gao +1
The presence of noise in acquired data invariably leads to performance degradation in cross-modal matching. Unfortunately, obtaining precise annotations in the multimodal field is…
GlanceVAD: Exploring Glance Supervision for Label-efficient Video Anomaly Detection
Huaxin Zhang, Xiang Wang, Xiaohao Xu +6
In recent years, video anomaly detection has been extensively investigated in both unsupervised and weakly supervised settings to alleviate costly temporal labeling. Despite signif…
Spatial Cascaded Clustering and Weighted Memory for Unsupervised Person Re-identification
Jiahao Hong, Jialong Zuo, Chuchu Han +4
Recent unsupervised person re-identification (re-ID) methods achieve high performance by leveraging fine-grained local context. These methods are referred to as part-based methods.…
SCTNet: Single-Branch CNN with Transformer Semantic Information for Real-Time Segmentation
Zhengze Xu, Dongyue Wu, Changqian Yu +3
Recent real-time semantic segmentation methods usually adopt an additional semantic branch to pursue rich long-range context. However, the additional branch incurs undesirable comp…