KY
Kim-Hui Yap
cs.CVcs.AIcs.LGeess.IVcs.CLcs.MMstat.MLAlgorithmseess.SPArtificial Intelligence
On Valency
published · living versionsW_f8c52ey4·v1 · currentpublished
S-Agent 2.0: Spatial Reasoning with a General Coding Agent
with Rui Gong, Ruoyu Wang, Yalun Dai, Hao Li +7
1 version
W_xerp8nge·v1published
Preprints & journals
49 papers in the corpus · 2005–2026S-Agent 2.0: Spatial Reasoning with a General Coding Agent2610.28354v1 · Rui Gong, Ruoyu Wang, Yalun Dai et al.2026 · 0 citationsarXivon Valency
MM-LeJEPA: Correlated Gaussian Regularization for Multimodal Joint-Embedding Predictive Architectures2610.24681v1 · Haowen Bai, Rui Gong$, Meichen Liu et al.2026 · 0 citationsarXivon Valency
Video-HopChain: Multi-Hop Questions and Confidence-Gated Exploration for Video Reasoning Models2609.25773v2 · Trung Nguyen Quang, Yuhao Dong, Shuo Sun et al.2026 · 0 citationsarXiv
SWE-Review: Closing the Loop on Issue Resolution with Agentic Code Review2607.06065v1 · Ruoyu Wang, Jierun Chen, Shaowei Wang et al.2026 · 0 citationsarXiv
S-Agent: Spatial Tool-Use Elicits Reasoning for Spatial Intelligence2606.20515v3 · Yalun Dai, Hao Li, Shulin Tian et al.2026 · 0 citationsarXiv
Demystifying Data Organization for Enhanced LLM Training2605.30334v1 · Yalun Dai, Yangyu Huang, Tongshen Yang et al.2026 · 0 citationsarXiv
NTIRE 2026 Challenge on Bitstream-Corrupted Video Restoration: Methods and Results2604.06945v3 · Wenbin Zou, Tianyi Liu, Kejun Wu et al.2026 · 0 citationsarXiv
Mixture-of-Modality-Experts with Holistic Token Learning for Fine-Grained Multimodal Visual Analytics in Driver Action Recognition2604.05947v1 · Tianyi Liu, Yiming Li, Wenqian Wang et al.2026 · 0 citationsarXiv
Accelerating Diffusion-based Video Editing via Heterogeneous Caching: Beyond Full Computing at Sampled Denoising Timestep2603.24260v1 · Tianyi Liu, Ye Lu, Linfeng Zhang et al.2026 · 0 citationsarXiv
MuseAgent-1: Interactive Grounded Multimodal Understanding of Music Scores and Performance Audio2601.11968v1 · Qihao Zhao, Yunqi Cao, Yangyu Huang et al.2026 · 0 citationsarXiv
DAOS: A Multimodal In-cabin Behavior Monitoring with Driver Action-Object Synergy Dataset2601.11990v2 · Yiming Li, Dan Lin, Wenfei Liang et al.2026 · 0 citationsarXiv
Building Egocentric Procedural AI Assistant: Methods, Benchmarks, and Challenges2511.13261v2 · Junlong Li, Huaiyuan Xu, Sijie Cheng et al.2025 · 0 citationsarXiv
Towards Blind Bitstream-corrupted Video Recovery via a Visual Foundation Model-driven Framework2507.22481v1 · Tianyi Liu, Kejun Wu, Chen Cai et al.2025 · 1 citationProceedings of the 33rd ACM International Conference on Multimedia, 2025
A Structure-aware and Motion-adaptive Framework for 3D Human Pose Estimation with Mamba2507.19852v1 · Ye Lu, Jie Wang, Jianjun Gao et al.2025 · 4 citationsarXiv
PromptSR: Cascade Prompting for Lightweight Image Super-Resolution2507.04118v1 · Wenyang Liu, Chen Cai, Jianjun Gao et al.2025 · 4 citationsarXiv
SSH-Net: A Self-Supervised and Hybrid Network for Noisy Image Watermark Removal2505.05088v1 · Wenyang Liu, Jianjun Gao, Kim-Hui Yap2025 · 1 citationarXiv
ByteNet: Rethinking Multimedia File Fragment Classification through Visual Perspectives2410.20855v1 · Wenyang Liu, Kejun Wu, Tianyi Liu et al.2024 · 21 citationsarXiv
CL-HOI: Cross-Level Human-Object Interaction Distillation from Vision Large Language Models2410.15657v1 · Jianjun Gao, Chen Cai, Ruoyu Wang et al.2024 · 0 citationsarXiv
Open World Object Detection: A Survey2410.11301v2 · Yiming Li, Yi Wang, Wenqian Wang et al.2024 · 34 citationsarXiv
Empowering Large Language Model for Continual Video Question Answering with Collaborative Prompting2410.00771v2 · Chen Cai, Zheng Wang, Jianjun Gao et al.2024 · 4 citationsarXiv
MultiFuser: Multimodal Fusion Transformer for Enhanced Driver Action Recognition2408.01766v2 · Ruoyu Wang, Wenqian Wang, Jianjun Gao et al.2024 · 5 citationsarXiv
CM2-Net: Continual Cross-Modal Mapping Network for Driver Action Recognition2406.11340v3 · Ruoyu Wang, Chen Cai, Wenqian Wang et al.2024 · 1 citationarXiv
Video sentence grounding with temporally global textual knowledge2404.13611v2 · Cai Chen, Runzhong Zhang, Jianjun Gao et al.2024 · 0 citationsarXiv
Multifocal multiview imaging and data compression based on angular-focal-spatial representation.38300059 · Wu, Kejun, Liu, Qiong, Yap, Kim-Hui et al.2024 · 8 citationsOptics letters. 2024;49(3):562-565
Multi-modality action recognition based on dual feature shift in vehicle cabin monitoring2401.14838v1 · Dan Lin, Philip Hann Yung Lee, Yiming Li et al.2024 · 12 citationsarXiv
High dimensional optical data - varifocal multiview imaging, compression and evaluation.38041269 · Wu, Kejun, Liu, Qiong, Yap, Kim-Hui et al.2023 · 9 citationsOptics express. 2023;31(24):39483-39499
Learning-Based Biharmonic Augmentation for Point Cloud Classification2311.06070v1 · Jiacheng Wei, Guosheng Lin, Henghui Ding et al.2023 · 1 citationarXiv
Bitstream-Corrupted Video Recovery: A Novel Benchmark Dataset and Method2309.13890v2 · Tianyi Liu, Kejun Wu, Yi Wang et al.2023 · 5 citationsarXiv
OccluTrack: Rethinking Awareness of Occlusion for Enhancing Multiple Pedestrian Tracking2309.10360v2 · Jianjun Gao, Yi Wang, Kim-Hui Yap et al.2023 · 5 citationsarXiv
Top-Down Framework for Weakly-supervised Grounded Image Captioning2306.07490v3 · Chen Cai, Suchen Wang, Kim-hui Yap et al.2023 · 33 citationsarXiv
SSN: Stockwell Scattering Network for SAR Image Change Detection2304.11404v1 · Gong Chen, Yanan Zhao, Yi Wang et al.2023 · 12 citationsIEEE Geoscience and Remote Sensing Letters, 2023
Bitstream-Corrupted JPEG Images are Restorable: Two-stage Compensation and Alignment Framework for Image Restoration2304.06976v1 · Wenyang Liu, Yi Wang, Kim-Hui Yap et al.2023 · 14 citationsarXiv
A Byte Sequence is Worth an Image: CNN for File Fragment Classification Using Bit Shift and n-Gram Embeddings2304.06983v1 · Wenyang Liu, Yi Wang, Kejun Wu et al.2023 · 14 citationsarXiv
TAPS3D: Text-Guided 3D Textured Shape Generation from Pseudo Supervision2303.13273v1 · Jiacheng Wei, Hao Wang, Jiashi Feng et al.2023 · 23 citationsarXiv
Dense Supervision Propagation for Weakly Supervised Semantic Segmentation on 3D Point Clouds2107.11267v3 · Jiacheng Wei, Guosheng Lin, Kim-Hui Yap et al.2021 · 17 citationsarXiv
Reconciliation of Statistical and Spatial Sparsity For Robust Image and Image-Set Classification2106.00256v1 · Hao Cheng, Kim-Hui Yap, Bihan Wen2021 · 1 citationarXiv
Empirical Analysis of Overfitting and Mode Drop in GAN Training2006.14265v1 · Yasin Yazici, Chuan-Sheng Foo, Stefan Winkler et al.2020 · 31 citationsarXiv
Multi-Path Region Mining For Weakly Supervised 3D Semantic Segmentation on Point Clouds2003.13035v1 · Jiacheng Wei, Guosheng Lin, Kim-Hui Yap et al.2020 · 148 citationsarXiv
AANet: Attribute Attention Network for Person Re-Identifications1912.09021v1 · Chiat-Pin Tay, Sharmili Roy, Kim-Hui Yap2019 · 380 citationsarXiv
Semantic Granularity Metric Learning for Visual Search1911.06047v1 · Dipu Manandhar, Muhammet Bastan, Kim-Hui Yap2019 · 11 citationsarXiv
Venn GAN: Discovering Commonalities and Particularities of Multiple Distributions1902.03444v1 · Yasin Yaz\icı, Bruno Lecouat, Chuan-Sheng Foo et al.2019 · 1 citationarXiv
DCI: Discriminative and Contrast Invertible Descriptor1901.00027v1 · Zhenwei Miao, Kim-Hui Yap, Xudong Jiang et al.2018 · 0 citationsarXiv
Interest Point Detection based on Adaptive Ternary Coding1901.00031v1 · Zhenwei Miao, Kim-Hui Yap, Xudong Jiang2018 · 0 citationsarXiv
The Unusual Effectiveness of Averaging in GAN Training1806.04498v2 · Yasin Yaz\icı, Chuan-Sheng Foo, Stefan Winkler et al.2018 · 96 citationsarXiv
Remote Detection of Idling Cars Using Infrared Imaging and Deep Networks1804.10805v1 · Muhammet Bastan, Kim-Hui Yap, Lap-Pui Chau2018 · 11 citationsarXiv
Contrast Invariant Interest Point Detection by Zero-Norm LoG Filter.26302514 · Zhenwei Miao, Xudong Jiang, Kim-Hui Yap2016 · 14 citationsIEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 2016;25(1):331-42
Discriminative BoW framework for mobile landmark recognition.23846513 · Chen, Tao, Yap, Kim-Hui2015 · 41 citationsIEEE transactions on cybernetics. 2014;44(5):695-706
A nonlinear least square technique for simultaneous image registration and super-resolution.17990759 · He, Yu, Yap, Kim-Hui, Chen, Li et al.2007 · 115 citationsIEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 2007;16(11):2830-41
A soft double regularization approach to parametric blind image deconvolution.15887557 · Chen, Li, Yap, Kim-Hui2005 · 45 citationsIEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 2005;14(5):624-33
Career total: 215 works. 49 are in this corpus.
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.