30 citations · 61 across the 18 of their papers we have counts for
21 papers
Thinking Beyond Videos: Unifying Video Reasoning and Deep Research for Open-World Video Agents
Wenqi Liu, Shijie Ma, Yunxiao Wang +21
Open-world video understanding often requires a model to locate sparse visual evidence and acquire external knowledge that is absent from the video and its parametric memory. While…
EmAvatar: Multimodal Empathetic Response Generation via Conflict Resolution and Expressive Guidance
Xiaolin Chen, Xuemeng Song, Jinlan Fu +3
Avatar-based multimodal empathetic response generation has emerged as a pivotal capability in human-centric systems, aiming to recognize user emotions and synthesize responses with…
ArtECulture: Benchmarking Culture-Conditioned Visual Emotion Understanding in Multimodal Large Language Models
Xiaolin Chen, Xuemeng Song, Wenhao Shi +3
Existing visual emotion understanding methods typically ignore cultural variations in emotional perception. We introduce culture-conditioned visual emotion understanding, a task th…
FiRE: Enhancing MLLMs with Fine-Grained Context Learning for Complex Image Retrieval
Bohan Hou, Haoqiang Lin, Xuemeng Song +4
Due to their strong generalizable multimodal processing and reasoning capabilities, Multimodal Large Language Models (MLLMs) have demonstrated significant potential as universal im…
Diverse-Intent Multi-Turn Fashion Image Retrieval
Mingqiang Tang, Haokun Wen, Meng Liu +3
Real-world fashion search involves interactive retrieval across multiple turns. However, existing multi-turn retrieval methods are built on a restrictive assumption that every inte…
FashionLens: Toward Versatile Fashion Image Retrieval via Task-Adaptive Learning
Haokun Wen, Xuemeng Song, Xinghao Xie +3
Fashion image retrieval is a cornerstone of modern e-commerce systems. A unified framework that supports diverse query formats and search intentions is highly desired in practice.…
OSGNet with MLLM Reranking @ Ego4D Episodic Memory Challenge 2026
Yisen Feng, Leigang Qu, Haoyu Zhang +5
In this report, we present our champion solutions for the Natural Language Queries and GoalStep tracks of the Ego4D Episodic Memory Challenge at CVPR 2026. Both tracks require accu…
InterLV-Search: Benchmarking Interleaved Multimodal Agentic Search
Bohan Hou, Jiuning Gu, Jiayan Guo +5
Existing benchmarks for multimodal agentic search evaluate multimodal search and visual browsing, but visual evidence is either confined to the input or treated as an answer endpoi…
UniCVR: From Alignment to Reranking for Unified Zero-Shot Composed Visual Retrieval
Haokun Wen, Xuemeng Song, Haoyu Zhang +3
Composed image retrieval, multi-turn composed image retrieval, and composed video retrieval all share a common paradigm: composing the reference visual with modification text to re…
VideoTemp-o3: Harmonizing Temporal Grounding and Video Understanding in Agentic Thinking-with-Videos
Wenqi Liu, Yunxiao Wang, Shijie Ma +14
In long-video understanding, conventional uniform frame sampling often fails to capture key visual evidence, leading to degraded performance and increased hallucinations. To addres…
Dual Knowledge-Enhanced Two-Stage Reasoner for Multimodal Dialog Systems
Xiaolin Chen, Xuemeng Song, Haokun Wen +3
Textual response generation is pivotal for multimodal \mbox{task-oriented} dialog systems, which aims to generate proper textual responses based on the multimodal context. While ex…
OFFSET: Segmentation-based Focus Shift Revision for Composed Image Retrieval
Zhiwei Chen, Yupeng Hu, Zixu Li +3
Composed Image Retrieval (CIR) represents a novel retrieval paradigm that is capable of expressing users' intricate retrieval requirements flexibly. It enables the user to give a m…
Fine-grained Textual Inversion Network for Zero-Shot Composed Image Retrieval
Haoqiang Lin, Haokun Wen, Xuemeng Song +3
Composed Image Retrieval (CIR) allows users to search target images with a multimodal query, comprising a reference image and a modification text that describes the user's modifica…
A Comprehensive Survey on Composed Image Retrieval
Xuemeng Song, Haoqiang Lin, Haokun Wen +3
Composed Image Retrieval (CIR) is an emerging yet challenging task that allows users to search for target images using a multimodal query, comprising a reference image and a modifi…
Content-aware Balanced Spectrum Encoding in Masked Modeling for Time Series Classification
Yudong Han, Haocong Wang, Yupeng Hu +3
Due to the superior ability of global dependency, transformer and its variants have become the primary choice in Masked Time-series Modeling (MTM) towards time-series classificatio…
Vision-guided and Mask-enhanced Adaptive Denoising for Prompt-based Image Editing
Kejie Wang, Xuemeng Song, Meng Liu +2
Text-to-image diffusion models have demonstrated remarkable progress in synthesizing high-quality images from text prompts, which boosts researches on prompt-based image editing th…
Pseudo-triplet Guided Few-shot Composed Image Retrieval
Bohan Hou, Haoqiang Lin, Haokun Wen +3
Composed Image Retrieval (CIR) is a challenging task that aims to retrieve the target image with a multimodal query, i.e., a reference image, and its complementary modification tex…
Simple but Effective Raw-Data Level Multimodal Fusion for Composed Image Retrieval
Haokun Wen, Xuemeng Song, Xiaolin Chen +3
Composed image retrieval (CIR) aims to retrieve the target image based on a multimodal query, i.e., a reference image paired with corresponding modification text. Recent CIR studie…
MMGRec: Multimodal Generative Recommendation with Transformer Model
Han Liu, Yinwei Wei, Xuemeng Song +3
Multimodal recommendation aims to recommend user-preferred candidates based on her/his historically interacted items and associated multimodal information. Previous studies commonl…
Interactive Garment Recommendation with User in the Loop
Federico Becattini, Xiaolin Chen, Andrea Puccia +4
Recommending fashion items often leverages rich user profiles and makes targeted suggestions based on past history and previous purchases. In this paper, we work under the assumpti…
Prompt-based Multi-interest Learning Method for Sequential Recommendation
Xue Dong, Xuemeng Song, Tongliang Liu +1
Multi-interest learning method for sequential recommendation aims to predict the next item according to user multi-faceted interests given the user historical interactions. Existin…