Author name cluster

Zhihang Liu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

2 author rows

AAAI Conference 2026 Conference Paper

RegionRAG: Region-level Retrieval-Augmented Generation for Visual Document Understanding

Yinglu Li
Zhiying Lu
Zhihang Liu
Yiwei Sun
Chuanbin Liu
Hongtao Xie

Multi-modal Retrieval-Augmented Generation (RAG) has become a critical method for empowering LLMs by leveraging candidate visual documents. However, current methods consider the entire document as the basic retrieval unit, introducing substantial irrelevant visual content in two ways: 1) Relevant documents often contain large regions unrelated to the query, diluting the focus on salient information; 2) Retrieving multiple documents to increase recall further introduces redundant and irrelevant documents. These redundant contexts distract the model's attention and further degrade the performance. To address this challenge, we propose RegionRAG, a novel framework that shifts the retrieval paradigm from the document level to the region level. During training, we design a hybrid supervision strategy from both labeled data and unlabeled data to pinpoint relevant patches. During inference, we propose a dynamic pipeline that intelligently groups salient patches into complete semantic regions. By delegating the task of identifying relevant regions to the retriever, RegionRAG enables the generator to focus solely on concise, query-relevant visual content, improving both efficiency and accuracy. Experiments on six benchmarks demonstrate that RegionRAG achieves state-of-the-art performance. It improves retrieval accuracy by 10.02% in R@1 on average, and boosts question answering accuracy by 3.56% while using only 71.42% visual tokens compared with prior methods.

PDF Details DOI

AAAI Conference 2026 Conference Paper

SpaceVLLM: Endowing Multimodal Large Language Model with Spatio-Temporal Video Grounding Capability

Jiankang Wang
Zhihan Zhang
Zhihang Liu
Yang Li
Jiannan Ge
Hongtao Xie
Yongdong Zhang

Multimodal Large Language Models (MLLMs) have shown remarkable progress in temporal or spatial localization tasks, but struggle with joint spatio-temporal video grounding (STVG). We identify two key bottlenecks hindering this capability: (1) the sheer number of visual tokens makes long-range and fine-grained visual modeling challenging; (2) generating a long sequence of bounding boxes in text makes it hard to accurately align each box with its specific video frame. Distinct from prior efforts that rely on attaching complex modules, we argue for a more elegant paradigm that unlocks the inherent potential of MLLMs and leverages their strengths. To this end, we propose \textbf{\textit{SpaceVLLM}}, a MLLM equipped with spatio-temporal video grounding capabilities. Specifically, we propose Spatio-Temporal Aware Queries, interleaved with video frames, to guide the MLLM in capturing both static appearance and dynamic motion features. We further present a lightweight Query-Guided Space Head that maps queries to precise spatial coordinates, bypassing the need for direct textual coordinate generation and enabling the MLLM to focus on video understanding. To further facilitate research in this area, we propose an automated data synthesis pipeline to construct \textbf{V-STG} dataset, comprising 110K STVG instances. Extensive experiments show that \textit{SpaceVLLM} achieves the state-of-the-art performance on STVG benchmarks and maintains strong performance on various video understanding tasks, validating our approach's effectiveness.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

CAPability: A Comprehensive Visual Caption Benchmark for Evaluating Both Correctness and Thoroughness

Zhihang Liu
Chen-Wei Xie
Bin Wen
Feiwu Yu
Pandeng Li
Boqiang Zhang
Nianzu Yang
Zuan Gao

Visual captioning benchmarks have become outdated with the emergence of modern multimodal large language models (MLLMs), as the brief ground-truth sentences and traditional metrics fail to assess detailed captions effectively. While recent benchmarks attempt to address this by focusing on keyword extraction or object-centric evaluation, they remain limited to vague-view or object-view analyses and incomplete visual element coverage. In this paper, we introduce CAPability, a comprehensive multi-view benchmark for evaluating visual captioning across 12 dimensions spanning six critical views. We curate nearly 11K human-annotated images and videos with visual element annotations to evaluate the generated captions. CAPability stably assesses both the correctness and thoroughness of captions with \textit{precision} and \textit{hit} metrics. By converting annotations to QA pairs, we further introduce a heuristic metric, \textit{know but cannot tell} ($K\bar{T}$), indicating a significant performance gap between QA and caption capabilities. Our work provides a holistic analysis of MLLMs' captioning abilities, as we identify their strengths and weaknesses across various dimensions, guiding future research to enhance specific aspects of their capabilities.

PDF Details

ECAI Conference 2024 Conference Paper

CLIP-based Cross-Level Semantic Interaction and Recombination Network for Composed Image Retrieval

Zhihang Liu
Qiang Huang
Yingying Zhu 0001

Composed image retrieval seeks to retrieve a target image that fulfills both modalities based on the user’s query, which comprises a modified text and a reference image. Although existing studies introduce novel multi-modal feature fusion techniques at the global or local level, they ignore exploring the cross-level semantic correspondence and recombining the original and target features in the reference image and the modified text, and the problems of modal inconsistency. To address these issues, we propose a CLIP-based Cross-Level Semantic Interaction and Recombination Network (SeIR). Specifically, we first resort the image and text encoders of the CLIP pre-trained model to narrow the modal gap between image and text, and extract both global and local features. We also introduce a cross-modal attention mechanism to screen out original and target features by exploring the semantic correlation between the cross-level image and text features. Subsequently, to alleviate the modal difference between the generated composed query representation and the target image, we utilize an affine transformation technique to recombine the original and target features from the image and text. Extensive experiments on the FashionIQ and CIRR benchmark datasets demonstrate the competitive performance of the proposed SeIR compared to the state-of-the-art methods.

Details

AAAI Conference 2024 Conference Paper

Towards Balanced Alignment: Modal-Enhanced Semantic Modeling for Video Moment Retrieval

Zhihang Liu
Jun Li
Hongtao Xie
Pandeng Li
Jiannan Ge
Sun-Ao Liu
Guoqing Jin

Video Moment Retrieval (VMR) aims to retrieve temporal segments in untrimmed videos corresponding to a given language query by constructing cross-modal alignment strategies. However, these existing strategies are often sub-optimal since they ignore the modality imbalance problem, i.e., the semantic richness inherent in videos far exceeds that of a given limited-length sentence. Therefore, in pursuit of better alignment, a natural idea is enhancing the video modality to filter out query-irrelevant semantics, and enhancing the text modality to capture more segment-relevant knowledge. In this paper, we introduce Modal-Enhanced Semantic Modeling (MESM), a novel framework for more balanced alignment through enhancing features at two levels. First, we enhance the video modality at the frame-word level through word reconstruction. This strategy emphasizes the portions associated with query words in frame-level features while suppressing irrelevant parts. Therefore, the enhanced video contains less redundant semantics and is more balanced with the textual modality. Second, we enhance the textual modality at the segment-sentence level by learning complementary knowledge from context sentences and ground-truth segments. With the knowledge added to the query, the textual modality thus maintains more meaningful semantics and is more balanced with the video modality. By implementing two levels of MESM, the semantic information from both modalities is more balanced to align, thereby bridging the modality gap. Experiments on three widely used benchmarks, including the out-of-distribution settings, show that the proposed framework achieves a new start-of-the-art performance with notable generalization ability (e.g., 4.42% and 7.69% average gains of R1@0.7 on Charades-STA and Charades-CG). The code will be available at https://github.com/lntzm/MESM.

PDF Details DOI