DH
Di Hu
cs.CVcs.MMcs.AIcs.SDeess.AScs.LGcs.ROcs.CLcs.HCcs.IR
On Valency
published · living versionsW_3fter5xf·v1 · currentpublished
From Reasoning to Action: Consequence-Grounded Alignment for Vision-Language-Action Models
with Yixue Zhang, Wenke Xia, Kun Wu, Wenbo Yu +4
1 version
Preprints & journals
54 papers in the corpus · 2017–2026Robust Audio-Visual Question Answering With Missing Modality in Training and Testing.42594008 · Zhou, Jinxing, Li, Zhangbin, Hu, Di et al.2026 · 0 citationsIEEE transactions on pattern analysis and machine intelligence. 2026;48(11):15347-15364
MIBench: Evaluating LMMs on Multimodal Interaction2603.13427v1 · Yu Miao, Zequn Yang, Yake Wei et al.2026 · 0 citationsarXiv
Object-AVEdit: An Object-level Audio-Visual Editing Model2510.00050v1 · Youquan Fu, Ruiyang Si, Hongfa Wang et al.2025 · 0 citationsarXiv
Human-assisted Robotic Policy Refinement via Action Preference Optimization2506.07127v3 · Wenke Xia, Yichu Yang, Hongtao Wu et al.2025 · 1 citationarXiv
Phoenix: A Motion-based Self-Reflection Framework for Fine-grained Robotic Action Correction2504.14588v1 · Wenke Xia, Ruoxuan Feng, Dong Wang et al.2025 · 5 citationsarXiv
Patch Matters: Training-free Fine-grained Image Caption Enhancement via Local Perception2504.06666v1 · Ruotian Peng, Haiying He, Yake Wei et al.2025 · 0 citationsarXiv
Adaptive Unimodal Regulation for Balanced Multimodal Information Acquisition2503.18595v1 · Chengxiang Huang, Yake Wei, Zequn Yang et al.2025 · 15 citationsarXiv
Crab: A Unified Audio-Visual Scene Understanding Model with Explicit Cooperation2503.13068v1 · Henghui Du, Guangyao Li, Chang Zhou et al.2025 · 4 citationsarXiv
Enhancing Modality Representation and Alignment for Multimodal Cold-start Active Learning2412.09126v1 · Meng Shen, Yake Wei, Jianxiong Yin et al.2024 · 1 citationarXiv
On-the-Fly Modulation for Balanced Multimodal Learning.39321012 · Wei, Yake, Hu, Di, Du, Henghui et al.2025 · 30 citationsIEEE transactions on pattern analysis and machine intelligence. 2025;47(1):469-485
Depth Helps: Improving Pre-trained RGB-based Policy with Depth Information Injection2408.05107v1 · Xincheng Pang, Wenke Xia, Zhigang Wang et al.2024 · 3 citationsarXiv
Boosting Audio Visual Question Answering via Key Semantic-Aware Cues2407.20693v1 · Guangyao Li, Henghui Du, Di Hu2024 · 19 citationsarXiv
Unveiling and Mitigating Bias in Audio Visual Segmentation2407.16638v1 · Peiwen Sun, Honggang Zhang, Di Hu2024 · 8 citationsarXiv
Stepping Stones: A Progressive Training Strategy for Audio-Visual Semantic Segmentation2407.11820v3 · Juncheng Ma, Peiwen Sun, Yaoting Wang et al.2024 · 11 citationsarXiv
Can Textual Semantics Mitigate Sounding Object Segmentation Preference?2407.10947v1 · Yaoting Wang, Peiwen Sun, Yuanchao Li et al.2024 · 8 citationsarXiv
Ref-AVS: Refer and Segment Objects in Audio-Visual Scenes2407.10957v1 · Yaoting Wang, Peiwen Sun, Dongzhan Zhou et al.2024 · 12 citationsarXiv
Diagnosing and Re-learning for Balanced Multimodal Learning2407.09705v1 · Yake Wei, Siwei Li, Ruoxuan Feng et al.2024 · 31 citationsarXiv
SphereDiffusion: Spherical Geometry-Aware Distortion Resilient Diffusion Model2403.10044v1 · Tao Wu, Xuewei Li, Zhongang Qi et al.2024 · 16 citationsarXiv
Kinematic-aware Prompting for Generalizable Articulated Object Manipulation with LLMs2311.02847v4 · Wenke Xia, Dong Wang, Xincheng Pang et al.2023 · 23 citationsarXiv
Prompting Segmentation with Sound Is Generalizable Audio-Visual Source Localizer2309.07929v3 · Yaoting Wang, Weisong Liu, Guangyao Li et al.2023 · 33 citationsarXiv
Enhancing multimodal cooperation via sample-level modality valuation2309.06255v4 · Yake Wei, Ruoxuan Feng, Zihe Wang et al.2023 · 43 citationsarXiv
Progressive Spatio-temporal Perception for Audio-Visual Question Answering2308.05421v1 · Guangyao Li, Wenxuan Hou, Di Hu2023 · 41 citationsarXiv
Towards Long Form Audio-visual Video Understanding2306.09431v1 · Wenxuan Hou, Guangyao Li, Yapeng Tian et al.2023 · 0 citationsarXiv
Multi-Scale Attention for Audio Question Answering2305.17993v1 · Guangyao Li, Yixin Xu, Di Hu2023 · 15 citationsarXiv
Robust Cross-Modal Knowledge Distillation for Unconstrained Videos2304.07775v2 · Wenke Xia, Xingjian Li, Andong Deng et al.2023 · 4 citationsarXiv
MMCosine: Multi-Modal Cosine Loss Towards Balanced Audio-Visual Fine-Grained Learning2303.05338v2 · Ruize Xu, Ruoxuan Feng, Shi-Xiong Zhang et al.2023 · 39 citationsarXiv
Revisiting Pre-training in Audio-Visual Learning2302.03533v2 · Ruoxuan Feng, Wenke Xia, Di Hu2023 · 2 citationsarXiv
TikTalk: A Video-Based Dialogue Dataset for Multi-Modal Chitchat in Real World2301.05880v3 · Hongpeng Lin, Ludan Ruan, Wenke Xia et al.2023 · 11 citationsarXiv
Learning in Audio-visual Context: A Review, Analysis, and New Perspective2208.09579v1 · Yake Wei, Di Hu, Yapeng Tian et al.2022 · 36 citationsarXiv
Dual Domain-Adversarial Learning for Audio-Visual Saliency Prediction2208.05220v2 · Yingzi Fan, Longfei Han, Yue Zhang et al.2022 · 1 citationarXiv
Balanced Multimodal Learning via On-the-fly Gradient Modulation2203.15332v1 · Xiaokang Peng, Yake Wei, Andong Deng et al.2022 · 366 citationsarXiv
Learning to Answer Questions in Dynamic Audio-Visual Scenarios2203.14072v2 · Guangyao Li, Yake Wei, Yapeng Tian et al.2022 · 122 citationsarXiv
SeCo: Separating Unknown Musical Visual Sounds with Consistency Guidance2203.13535v1 · Xinchi Zhou, Dongzhan Zhou, Wanli Ouyang et al.2022 · 5 citationsarXiv
Towards Inadequately Pre-trained Models in Transfer Learning2203.04668v3 · Andong Deng, Xingjian Li, Di Hu et al.2022 · 14 citationsarXiv
Visual Sound Localization in the Wild by Cross-Modal Interference Erasing2202.06406v1 · Xian Liu, Rui Qian, Hang Zhou et al.2022 · 26 citationsarXiv
Class-aware Sounding Objects Localization via Audiovisual Correspondence2112.11749v1 · Di Hu, Yake Wei, Rui Qian et al.2021 · 45 citationsarXiv
Integrating Structural Description of Data Format Information into Programming to Auto-generate File Reading Programs2110.05053v1 · Xinghua Cheng, Erjie Hu, Di Hu2021 · 0 citationsarXiv
Self-supervised Audiovisual Representation Learning for Remote Sensing Data2108.00688v2 · Konrad Heidler, Lichao Mou, Di Hu et al.2021 · 49 citationsInternational Journal of Applied Earth Observation and Geoinformation, Volume 116, 2023
Unsupervised Multi-Source Domain Adaptation for Person Re-Identification2104.12961v1 · Zechen Bai, Zhigang Wang, Jian Wang et al.2021 · 106 citationsarXiv
Cyclic Co-Learning of Sounding Object Visual Grounding and Sound Separation2104.02026v1 · Yapeng Tian, Di Hu, Chenliang Xu2021 · 68 citationsarXiv
Temporal Relational Modeling with Self-Supervision for Action Segmentation2012.07508v1 · Dong Wang, Di Hu, Xingjian Li et al.2020 · 51 citationsarXiv
Towards Accurate Knowledge Transfer via Target-awareness Representation Disentanglement2010.08532v2 · Xingjian Li, Di Hu, Xuhong Li et al.2020 · 1 citationarXiv
Discriminative Sounding Objects Localization via Self-supervised Audiovisual Matching2010.05466v1 · Di Hu, Rui Qian, Minyue Jiang et al.2020 · 88 citationsarXiv
Multiple Sound Sources Localization from Coarse to Fine2007.06355v2 · Rui Qian, Di Hu, Heinrich Dinkel et al.2020 · 154 citationsarXiv
Cross-Task Transfer for Geotagged Audiovisual Aerial Scene Recognition2005.08449v2 · Di Hu, Xuhong Li, Lichao Mou et al.2020 · 41 citationsarXiv
Ambient Sound Helps: Audiovisual Crowd Counting in Extreme Conditions2005.07097v2 · Di Hu, Lichao Mou, Qingzhong Wang et al.2020 · 30 citationsarXiv
Curriculum Audiovisual Learning2001.09414v1 · Di Hu, Zheng Wang, Haoyi Xiong et al.2020 · 30 citationsarXiv
Listen to the Image1904.09115v1 · Di Hu, Dong Wang, Xuelong Li et al.2019 · 0 citationsarXiv
Discrete Spectral Hashing for Efficient Similarity Retrieval.30307862 · Hu, Di, Nie, Feiping, Li, Xuelong2018 · 36 citationsIEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 2019;28(3):1080-1091
Deep LDA Hashing1810.03402v1 · Di Hu, Feiping Nie, Xuelong Li2018 · 0 citationsarXiv
Career total: 93 works. 54 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.