Profiles2020-2026
Hongtao Xie
University of Science and Technology of China
44Papers
9Last author
57Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers44
- SpaceVLLM: Endowing Multimodal Large Language Model with Spatio-Temporal Video Grounding CapabilityAuthor 6 of 7AAAI 2026 · 20 citations
- RegionRAG: Region-level Retrieval-Augmented Generation for Visual Document UnderstandingAuthor 6 of 6AAAI 2026 · 2 citations
- Seeing is Improving: Visual Feedback for Iterative Text Layout RefinementAuthor 4 of 4CVPR 2026 · 2 citations
- Towards Universal Open-Set Visual Font Recognition Via Augmented Synthetic SimilarityAuthor 5 of 5CVPR Findings 2026
- SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text RecognitionAuthor 3 of 5ICCV 2025 · 22 citations
- Forensic-MoE: Exploring Comprehensive Synthetic Image Detection Traces With Mixture of ExpertsAuthor 5 of 6ICCV 2025 · 4 citations
- CLIP-Adapted Region-to-Text Learning for Generative Open-Vocabulary Semantic SegmentationAuthor 3 of 8ICCV 2025 · 3 citations
- IDseq: Decoupled and Sequentially Detecting and Grounding Multi-Modal Media ManipulationAuthor 5 of 5AAAI 2025 · 2 citations
- Igd: Instructional Graphic Design With Multimodal Layer GeneratioAuthor 6 of 7ICCV 2025 · 1 citation
- Hybrid-Level Instruction Injection for Video Token Compression in Multi-modal Large Language ModelsAuthor 8 of 8CVPR 2025
- Mask^2DiT: Dual Mask-based Diffusion Transformer for Multi-Scene Long Video GenerationAuthor 8 of 9CVPR 2025
- PosterMaker: Towards High-Quality Product Poster Generation with Accurate Text RenderingAuthor 7 of 7CVPR 2025
- DEADiff: An Efficient Stylization Diffusion Model with Disentangled RepresentationsAuthor 4 of 8CVPR 2024 · 57 citations
- Towards Balanced Alignment: Modal-Enhanced Semantic Modeling for Video Moment RetrievalAuthor 3 of 7AAAI 2024 · 49 citations
- DiffAM: Diffusion-Based Adversarial Makeup Transfer for Facial Privacy ProtectionAuthor 3 of 5CVPR 2024 · 35 citations
- OTE: Exploring Accurate Scene Text Recognition Using One TokenAuthor 3 of 4CVPR 2024 · 21 citations
- ShowMaker: Creating High-Fidelity 2D Human Video via Fine-Grained Diffusion ModelingAuthor 11 of 11NeurIPS 2024 · 21 citations
- How Control Information Influences Multilingual Text Image Generation and Editing?Author 4 of 4NeurIPS 2024 · 11 citations
- Choose What You Need: Disentangled Representation Learning for Scene Text Recognition, Removal and EditingAuthor 2 of 4CVPR 2024 · 9 citations
- Knowledge Context Modeling with Pre-trained Language Models for Contrastive Knowledge Graph CompletionAuthor 5 of 6ACL Findings 2024 · 9 citations
- Boosting Semi-Supervised Scene Text Recognition via Viewing and SummarizingAuthor 5 of 6NeurIPS 2024 · 6 citations
- MomentDiff: Generative Video Moment Retrieval from Random to RealAuthor 3 of 8NeurIPS 2023 · 113 citations
- Progressive Spatio-Temporal Prototype Matching for Text-Video RetrievalAuthor 4 of 8ICCV 2023 · 62 citations
- Exploring Stroke-Level Modifications for Scene Text EditingAuthor 3 of 6AAAI 2023 · 51 citations
- Symmetrical Linguistic Feature Distillation with CLIP for Scene Text RecognitionAuthor 2 of 5ACM MM 2023 · 31 citations
- TextPainter: Multimodal Text Image Generation with Visual-harmony and Text-comprehension for Poster DesignAuthor 5 of 7ACM MM 2023 · 6 citations
- Learning Orthogonal Prototypes for Generalized Few-Shot Semantic SegmentationAuthor 4 of 6CVPR 2023
- Bridging the Gap Between Vision Transformers and Convolutional Neural Networks on Small DatasetsAuthor 2 of 4NeurIPS 2022 · 107 citations
- Partial Class Activation Attention for Semantic SegmentationAuthor 2 of 5CVPR 2022 · 47 citations
- Geometry Aligned Variational Transformer for Image-conditioned Layout GenerationAuthor 5 of 7ACM MM 2022 · 37 citations
Showing the 30 most recent indexed papers.
