Skip to content
conftrace_

Paul Hongsuck Seo

32 papers · 2016–2026 · 10 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓
+10 more ↓ πŸ—ΊοΈ Taxonomy Completionist (68) πŸƒ Academic Marathon Β· Half 🌍 Conference Polyglot Β· Gold πŸŒ‰ Interdisciplinary Bridge Β· Gold 🐣 Hot Topic Early Bird
🌱 Topic Pioneer 🧬 Topic Evolution πŸ”¬ Deep Specialist (11) 🌈 Renaissance Researcher (5) πŸ”₯ Unstoppable Β· Silver ⚑ Prolific Year Β· Productive πŸš€ Conference Pioneer πŸ’Ž Century Club Β· Bronze πŸ“ˆ Trend Setter πŸ—ƒοΈ Keyword Collector (156)

Venues

CVPR (12) ECCV (4) Interspeech (4) NeurIPS (4) AAAI (2) ICCV (2) ACL (1) ACML (1) EMNLP (1) NAACL (1)

Top co-authors

Bohyung Han (9) Cordelia Schmid (7) Arsha Nagrani (7) Seokju Cho (3) Sumin An (3) Anurag Arnab (3) Seungryong Kim (3) Minsu Cho (3) Geonhee Han (2) Heeseong Shin (2)

Research topics

Deep Learning (16) Artificial Intelligence (15) Machine Learning (15) Computer Vision (14) Core AI Β· Artificial Intelligence (14) Learning Types Β· Deep Learning (11) Learning Types Β· Machine Learning (10) Natural Language Processing (8) Analysis (8) Architectures (6) Processing (6) Applications (5) Speech & Audio (4) Core AI Β· Computer Vision (4) Core Methods (4)

Keywords

zero-shot learning (5) multimodal learning (5) vision-language model (4) video understanding (4) semantic segmentation (3) visual grounding (2) deep neural network (2) multi-hop reasoning (2) instance segmentation (2) attention mechanism (2) generative model (2) automatic speech recognition (2) audio-visual speech recognition (2) question answering (2) object tracking (2) diffusion model (2) visual question answering (1) uncertainty quantification (1) vision transformer (1) sound source localization (1)

Papers

CRIT: Graph-Based Automatic Data Synthesis to Enhance Cross-Modal Multi-Hop Reasoning CVPR 2026 Bridging Audio and Vision: Zero-Shot Audiovisual Segmentation by Connecting Pretrained Models Interspeech 2025 Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries Interspeech 2025 DGMO: Training-Free Audio Source Separation through Diffusion-Guided Mask Optimization Interspeech 2025 DialNav: Multi-turn Dialog Navigation with a Remote Guide ICCV 2025 LCIRC: A Recurrent Compression Approach for Efficient Long-form Context and Query Dependent Modeling in LLMs NAACL 2025 Multi-Granularity Video Object Segmentation AAAI 2025 Random Conditioning for Diffusion Model Compression with Distillation CVPR 2025 ReSCORE: Label-free Iterative Retriever Training for Multi-hop Question Answering with Relevance-Consistency Supervision ACL 2025 ReTAG: Retrieval-Enhanced, Topic-Augmented Graph-Based Global Sensemaking EMNLP 2025 CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation CVPR 2024 Learning Correlation Structures for Vision Transformers CVPR 2024 Pseudo-RIS: Distinctive Pseudo-supervision Generation for Referring Image Segmentation ECCV 2024 Towards Open-Vocabulary Semantic Segmentation Without Semantic Labels NeurIPS 2024 TrackIME: Enhanced Video Point Tracking via Instance Motion Estimation NeurIPS 2024 AVFormer: Injecting Vision Into Frozen Speech Models for Zero-Shot AV-ASR CVPR 2023 IFSeg: Image-Free Semantic Segmentation via Vision-Language Model CVPR 2023 Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning CVPR 2023 Zero-Shot Referring Image Segmentation With Global-Local Context Features CVPR 2023 AVATAR: Unconstrained Audiovisual Speech Recognition Interspeech 2022 End-to-End Generative Pretraining for Multimodal Video Captioning CVPR 2022 Learning Audio-Video Modalities from Image Captions ECCV 2022 Look Before You Speak: Visually Contextualized Utterances CVPR 2021 Reinforcing an Image Caption Generator Using Off-Line Human Feedback AAAI 2020 Combinatorial Inference against Label Noise NeurIPS 2019 Learning for Single-Shot Confidence Calibration in Deep Neural Networks Through Stochastic Inferences CVPR 2019 Regularizing Neural Networks via Stochastic Branch Layers ACML 2019 Attentive Semantic Alignment with Offset-Aware Correlation Kernels ECCV 2018 CPlaNet: Enhancing Image Geolocalization by Combinatorial Partitioning of Maps ECCV 2018 MarioQA: Answering Questions by Watching Gameplay Videos ICCV 2017 Visual Reference Resolution using Attention Memory for Visual Dialog NeurIPS 2017 Image Question Answering Using Convolutional Neural Network With Dynamic Parameter Prediction CVPR 2016