36 citations · 53 across the 36 of their papers we have counts for
22 papers · 1 filter
Routing Before Looking: Query-Adaptive Evidence Acquisition for Long-form Video Understanding
Tianyue Wang, Xuying Wu, Yuxiang Ma +7
Long-form video understanding remains challenging for video agents due to the mismatch between query demands and evidence acquisition strategies. Although recent planning-before-pe…
PixVL: Self-Supervised Training of Pixel-Level MLLMs via a Unified Mask--Text Consistency Cycle
Yicheng Xiao, Haoxuan Ma, Caorui Li +7
Recent studies develop pixel-level multimodal large language models (MLLMs) that support both Region Segmentation and Region Understanding, extending multimodal interaction from wh…
ReLoop-UME: Recurrent Depth with Learnable Retrieval Registers for Universal Multimodal Embedding
Shijie Wang, Xiangzhao Hao, Yueti Li +3
Universal multimodal embedding (UME) maps heterogeneous multimodal inputs into a shared embedding space. Existing UME models either form embeddings through single forward encoding…
ST-Prune: Training-Free Spatio-Temporal Token Pruning for Vision-Language Models in Autonomous Driving
Lin Sha, Haiyun Guo, Tao Wang +4
Vision-Language Models (VLMs) have become central to autonomous driving systems, yet their deployment is severely bottlenecked by the massive computational overhead of multi-view c…
PLUME: Latent Reasoning Based Universal Multimodal Embedding
Chenwei He, Xiangzhao Hao, Tianyu Yang +6
Universal multimodal embedding (UME) maps heterogeneous inputs into a shared retrieval space with a single model. Recent approaches improve UME by generating explicit chain-of-thou…
CLEAR: Unlocking Generative Potential for Degraded Image Understanding in Unified Multimodal Models
Xiangzhao Hao, Zefeng Zhang, Zhenyu Zhang +6
Image degradation from blur, noise, compression, and poor illumination severely undermines multimodal understanding in real-world settings. Unified multimodal models that combine u…
ReCALL: Recalibrating Capability Degradation for MLLM-based Composed Image Retrieval
Tianyu Yang, Chenwei He, Xiangzhao Hao +6
Composed Image Retrieval (CIR) aims to retrieve target images based on a hybrid query comprising a reference image and a modification text. Early dual-tower Vision-Language Models…
WISER: Wider Search, Deeper Thinking, and Adaptive Fusion for Training-Free Zero-Shot Composed Image Retrieval
Tianyue Wang, Leigang Qu, Tianyu Yang +4
Zero-Shot Composed Image Retrieval (ZS-CIR) aims to retrieve target images given a multimodal query (comprising a reference image and a modification text), without training on anno…
TRACE: Task-Adaptive Reasoning and Representation Learning for Universal Multimodal Retrieval
Xiangzhao Hao, Shijie Wang, Tianyu Yang +3
Universal Multimodal Retrieval requires unified embedding models capable of interpreting diverse user intents, ranging from simple keywords to complex compositional instructions. W…
Active Zero: Self-Evolving Vision-Language Models through Active Environment Exploration
Jinghan He, Junfeng Fang, Feng Xiong +5
Self-play has enabled large language models to autonomously improve through self-generated challenges. However, existing self-play methods for vision-language models rely on passiv…
PixCLIP: Achieving Fine-grained Visual Language Understanding via Any-granularity Pixel-Text Alignment Learning
Yicheng Xiao, Yu Chen, Haoxuan Ma +5
While the Contrastive Language-Image Pretraining(CLIP) model has achieved remarkable success in a variety of downstream vison language understanding tasks, enhancing its capability…
UniFGVC: Universal Training-Free Few-Shot Fine-Grained Vision Classification via Attribute-Aware Multimodal Retrieval
Hongyu Guo, Xiangzhao Hao, Jiarui Guo +3
Few-shot fine-grained visual classification (FGVC) aims to discriminate between subtly different categories with very limited data. While Multimodal Large Language Models (MLLM) ex…
FOCUS: Fine-grained Optimization with Semantic Guided Understanding for Pedestrian Attributes Recognition
Hongyan An, Kuan Zhu, Xin He +4
Pedestrian attribute recognition (PAR) is a fundamental perception task in intelligent transportation and security. To tackle this fine-grained task, most existing methods focus on…
Referring Expression Instance Retrieval and A Strong End-to-End Baseline
Xiangzhao Hao, Kuan Zhu, Hongyu Guo +5
Using natural language to query visual information is a fundamental need in real-world applications. Text-Image Retrieval (TIR) retrieves a target image from a gallery based on an…
Steering LVLMs via Sparse Autoencoder for Hallucination Mitigation
Zhenglin Hua, Jinghan He, Zijun Yao +4
Large vision-language models (LVLMs) have achieved remarkable performance on multimodal tasks. However, they still suffer from hallucinations, generating text inconsistent with vis…
Monocular Lane Detection Based on Deep Learning: A Survey
Xin He, Haiyun Guo, Kuan Zhu +4
Lane detection plays an important role in autonomous driving perception systems. As deep learning algorithms gain popularity, monocular lane detection methods based on them have de…
ZBS: Zero-shot Background Subtraction via Instance-level Background Modeling and Foreground Selection
Yongqi An, Xu Zhao, Tao Yu +4
Background subtraction (BGS) aims to extract all moving objects in the video frames to obtain binary foreground segmentation masks. Deep learning has been widely used in this field…
Plug-and-Play Pseudo Label Correction Network for Unsupervised Person Re-identification
Tianyi Yan, Kuan Zhu, Haiyun guo +3
Clustering-based methods, which alternate between the generation of pseudo labels and the optimization of the feature extraction network, play a dominant role in both unsupervised…
PASS: Part-Aware Self-Supervised Pre-Training for Person Re-Identification
Kuan Zhu, Haiyun Guo, Tianyi Yan +3
In person re-identification (ReID), very recent researches have validated pre-training the models on unlabelled person images is much better than on ImageNet. However, these resear…
AAformer: Auto-Aligned Transformer for Person Re-Identification
Kuan Zhu, Haiyun Guo, Shiliang Zhang +4
In person re-identification (re-ID), extracting part-level features from person images has been verified to be crucial to offer fine-grained information. Most of the existing CNN-b…
Identity-Guided Human Semantic Parsing for Person Re-Identification
Kuan Zhu, Haiyun Guo, Zhiwei Liu +2
Existing alignment-based methods have to employ the pretrained human parsing models to achieve the pixel-level alignment, and cannot identify the personal belongings (e.g., backpac…
Semantic Alignment: Finding Semantically Consistent Ground-truth for Facial Landmark Detection
Zhiwei Liu, Xiangyu Zhu, Guosheng Hu +5
Recently, deep learning based facial landmark detection has achieved great success. Despite this, we notice that the semantic ambiguity greatly degrades the detection performance.…