Paul Hongsuck Seo

70 papers A* 17A 5C 1Journal 38Unranked 9

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Breaking the Visual Shortcuts in Multimodal Knowledge-Based Visual Question Answering. CoRR Dosung Lee, Sangwon Jung, Boyoung Kim, Minyoung Kim, SungYeon Kim, Junyoung Sung, Paul Hongsuck Seo
2025	A	`conf`	Bridging Audio and Vision: Zero-Shot Audiovisual Segmentation by Connecting Pretrained Models. INTERSPEECH Seung-jae Lee, Paul Hongsuck Seo
2025	J	`jnl`	Bridging Audio and Vision: Zero-Shot Audiovisual Segmentation by Connecting Pretrained Models. CoRR Seung-jae Lee, Paul Hongsuck Seo
2025	A	`conf`	Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries. INTERSPEECH Minyoung Kim, Sehwan Park, Sungmin Cha, Paul Hongsuck Seo
2025	J	`jnl`	Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries. CoRR Minyoung Kim, Sehwan Park, Sungmin Cha, Paul Hongsuck Seo
2025	A	`conf`	DGMO: Training-Free Audio Source Separation through Diffusion-Guided Mask Optimization. INTERSPEECH Geonyoung Lee, Geonhee Han, Paul Hongsuck Seo
2025	J	`jnl`	DGMO: Training-Free Audio Source Separation through Diffusion-Guided Mask Optimization. CoRR Geonyoung Lee, Geonhee Han, Paul Hongsuck Seo
2025	J	`jnl`	DialNav: Multi-turn Dialog Navigation with a Remote Guide. CoRR Leekyeung Han, Hyunji Min, Gyeom Hwangbo, Jonghyun Choi, Paul Hongsuck Seo
2025	J	`jnl`	Direct Diffusion Score Preference Optimization via Stepwise Contrastive Policy-Pair Supervision. CoRR Dohyun Kim, Seungwoo Lyu, Seung Wook Kim, Paul Hongsuck Seo
2025	J	`jnl`	GOAT: A Training Framework for Goal-Oriented Agent with Tools. CoRR Hyunji Min, Sangwon Jung, Junyoung Sung, Dosung Lee, Leekyeung Han, Paul Hongsuck Seo
2025	J	`jnl`	Image Diffusion Models Exhibit Emergent Temporal Propagation in Videos. CoRR Youngseo Kim, Dohyun Kim, Geonhee Han, Paul Hongsuck Seo
2025	—	`conf`	LCIRC: A Recurrent Compression Approach for Efficient Long-form Context and Query Dependent Modeling in LLMs. NAACL (Long Papers) Sumin An, Junyoung Sung, Wonpyo Park, Chanjun Park, Paul Hongsuck Seo
2025	J	`jnl`	LCIRC: A Recurrent Compression Approach for Efficient Long-form Context and Query Dependent Modeling in LLMs. CoRR Sumin An, Junyoung Sung, Wonpyo Park, Chanjun Park, Paul Hongsuck Seo
2025	A*	`conf`	Multi-Granularity Video Object Segmentation. AAAI Sangbeom Lim, Seongchan Kim, Seungjun An, Seokju Cho, Paul Hongsuck Seo, Seungryong Kim
2025	A*	`conf`	Random Conditioning for Diffusion Model Compression with Distillation. CVPR Dohyun Kim, Sehwan Park, Geonhee Han, Seung Wook Kim, Paul Hongsuck Seo
2025	J	`jnl`	Random Conditioning with Distillation for Data-Efficient Diffusion Model Compression. CoRR Dohyun Kim, Sehwan Park, Geonhee Han, Seung Wook Kim, Paul Hongsuck Seo
2025	—	`conf`	ReSCORE: Label-free Iterative Retriever Training for Multi-hop Question Answering with Relevance-Consistency Supervision. ACL (1) Dosung Lee, Wonjun Oh, Boyoung Kim, Minyoung Kim, Joonsuk Park, Paul Hongsuck Seo
2025	J	`jnl`	ReSCORE: Label-free Iterative Retriever Training for Multi-hop Question Answering with Relevance-Consistency Supervision. CoRR Dosung Lee, Wonjun Oh, Boyoung Kim, Minyoung Kim, Joonsuk Park, Paul Hongsuck Seo
2025	—	`conf`	ReTAG: Retrieval-Enhanced, Topic-Augmented Graph-Based Global Sensemaking. EMNLP (Findings) Boyoung Kim, Dosung Lee, Sumin An, Jinseong Jeong, Paul Hongsuck Seo
2025	J	`jnl`	ReTAG: Retrieval-Enhanced, Topic-Augmented Graph-Based Global Sensemaking. CoRR Boyoung Kim, Dosung Lee, Sumin An, Jinseong Jeong, Paul Hongsuck Seo
2025	J	`jnl`	Robust Image Self-Recovery against Tampering using Watermark Generation with Pixel Shuffling. CoRR Minyoung Kim, Paul Hongsuck Seo
2025	J	`jnl`	Seg4Diff: Unveiling Open-Vocabulary Segmentation in Text-to-Image Diffusion Transformers. CoRR Chaehyun Kim, Heeseong Shin, Eunbeen Hong, Heeji Yoon, Anurag Arnab, Paul Hongsuck Seo, Sunghwan Hong, Seungryong Kim
2025	J	`jnl`	Spectral-Adaptive Modulation Networks for Visual Perception. CoRR Guhnoo Yun, Juhan Yoo, Kijung Kim, Jeongho Lee, Paul Hongsuck Seo, Dong Hwan Kim
2024	A*	`conf`	CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation. CVPR Seokju Cho, Heeseong Shin, Sunghwan Hong, Anurag Arnab, Paul Hongsuck Seo, Seungryong Kim
2024	A*	`conf`	Learning Correlation Structures for Vision Transformers. CVPR Manjin Kim, Paul Hongsuck Seo, Cordelia Schmid, Minsu Cho
2024	J	`jnl`	Learning Correlation Structures for Vision Transformers. CoRR Manjin Kim, Paul Hongsuck Seo, Cordelia Schmid, Minsu Cho
2024	J	`jnl`	Multi-Granularity Video Object Segmentation. CoRR Sangbeom Lim, Seongchan Kim, Seungjun An, Seokju Cho, Paul Hongsuck Seo, Seungryong Kim
2024	—	`conf`	Pseudo-RIS: Distinctive Pseudo-Supervision Generation for Referring Image Segmentation. ECCV (68) Seonghoon Yu, Paul Hongsuck Seo, Jeany Son
2024	J	`jnl`	Pseudo-RIS: Distinctive Pseudo-supervision Generation for Referring Image Segmentation. CoRR Seonghoon Yu, Paul Hongsuck Seo, Jeany Son
2024	A*	`conf`	Towards Open-Vocabulary Semantic Segmentation Without Semantic Labels. NeurIPS Heeseong Shin, Chaehyun Kim, Sunghwan Hong, Seokju Cho, Anurag Arnab, Paul Hongsuck Seo, Seungryong Kim
2024	J	`jnl`	Towards Open-Vocabulary Semantic Segmentation Without Semantic Labels. CoRR Heeseong Shin, Chaehyun Kim, Sunghwan Hong, Seokju Cho, Anurag Arnab, Paul Hongsuck Seo, Seungryong Kim
2024	A*	`conf`	TrackIME: Enhanced Video Point Tracking via Instance Motion Estimation. NeurIPS Seong Hyeon Park, Huiwon Jang, Byungwoo Jeon, Sukmin Yun, Paul Hongsuck Seo, Jinwoo Shin
2023	A*	`conf`	AVFormer: Injecting Vision into Frozen Speech Models for Zero-Shot AV-ASR. CVPR Paul Hongsuck Seo, Arsha Nagrani, Cordelia Schmid
2023	J	`jnl`	AVFormer: Injecting Vision into Frozen Speech Models for Zero-Shot AV-ASR. CoRR Paul Hongsuck Seo, Arsha Nagrani, Cordelia Schmid
2023	J	`jnl`	CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation. CoRR Seokju Cho, Heeseong Shin, Sunghwan Hong, Seungjun An, Seungjun Lee, Anurag Arnab, Paul Hongsuck Seo, Seungryong Kim
2023	A*	`conf`	IFSeg: Image-free Semantic Segmentation via Vision-Language Model. CVPR Sukmin Yun, Seong Hyeon Park, Paul Hongsuck Seo, Jinwoo Shin
2023	J	`jnl`	IFSeg: Image-free Semantic Segmentation via Vision-Language Model. CoRR Sukmin Yun, Seong Hyeon Park, Paul Hongsuck Seo, Jinwoo Shin
2023	A*	`conf`	Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning. CVPR Antoine Yang, Arsha Nagrani, Paul Hongsuck Seo, Antoine Miech, Jordi Pont-Tuset, Ivan Laptev, Josef Sivic, Cordelia Schmid
2023	J	`jnl`	Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning. CoRR Antoine Yang, Arsha Nagrani, Paul Hongsuck Seo, Antoine Miech, Jordi Pont-Tuset, Ivan Laptev, Josef Sivic, Cordelia Schmid
2023	A*	`conf`	Zero-shot Referring Image Segmentation with Global-Local Context Features. CVPR Seonghoon Yu, Paul Hongsuck Seo, Jeany Son
2023	J	`jnl`	Zero-shot Referring Image Segmentation with Global-Local Context Features. CoRR Seonghoon Yu, Paul Hongsuck Seo, Jeany Son
2022	J	`jnl`	AVATAR submission to the Ego4D AV Transcription Challenge. CoRR Paul Hongsuck Seo, Arsha Nagrani, Cordelia Schmid
2022	A	`conf`	AVATAR: Unconstrained Audiovisual Speech Recognition. INTERSPEECH Valentin Gabeur, Paul Hongsuck Seo, Arsha Nagrani, Chen Sun, Karteek Alahari, Cordelia Schmid
2022	J	`jnl`	AVATAR: Unconstrained Audiovisual Speech Recognition. CoRR Valentin Gabeur, Paul Hongsuck Seo, Arsha Nagrani, Chen Sun, Karteek Alahari, Cordelia Schmid
2022	A*	`conf`	End-to-end Generative Pretraining for Multimodal Video Captioning. CVPR Paul Hongsuck Seo, Arsha Nagrani, Anurag Arnab, Cordelia Schmid
2022	J	`jnl`	End-to-end Generative Pretraining for Multimodal Video Captioning. CoRR Paul Hongsuck Seo, Arsha Nagrani, Anurag Arnab, Cordelia Schmid
2022	—	`conf`	Learning Audio-Video Modalities from Image Captions. ECCV (14) Arsha Nagrani, Paul Hongsuck Seo, Bryan Seybold, Anja Hauth, Santiago Manen, Chen Sun, Cordelia Schmid
2022	J	`jnl`	Learning Audio-Video Modalities from Image Captions. CoRR Arsha Nagrani, Paul Hongsuck Seo, Bryan Seybold, Anja Hauth, Santiago Manen, Chen Sun, Cordelia Schmid
2021	A*	`conf`	Look Before You Speak: Visually Contextualized Utterances. CVPR Paul Hongsuck Seo, Arsha Nagrani, Cordelia Schmid
2020	J	`jnl`	Look Before you Speak: Visually Contextualized Utterances. CoRR Paul Hongsuck Seo, Arsha Nagrani, Cordelia Schmid
2020	A*	`conf`	Reinforcing an Image Caption Generator Using Off-Line Human Feedback. AAAI Paul Hongsuck Seo, Piyush Sharma, Tomer Levinboim, Bohyung Han, Radu Soricut
2019	A*	`conf`	Combinatorial Inference against Label Noise. NeurIPS Paul Hongsuck Seo, Geeho Kim, Bohyung Han
2019	A*	`conf`	Learning for Single-Shot Confidence Calibration in Deep Neural Networks Through Stochastic Inferences. CVPR Seonguk Seo, Paul Hongsuck Seo, Bohyung Han
2019	C	`conf`	Regularizing Neural Networks via Stochastic Branch Layers. ACML Wonpyo Park, Paul Hongsuck Seo, Bohyung Han, Minsu Cho
2019	J	`jnl`	Regularizing Neural Networks via Stochastic Branch Layers. CoRR Wonpyo Park, Paul Hongsuck Seo, Bohyung Han, Minsu Cho
2019	J	`jnl`	Reinforcing an Image Caption Generator Using Off-Line Human Feedback. CoRR Paul Hongsuck Seo, Piyush Sharma, Tomer Levinboim, Bohyung Han, Radu Soricut
2018	—	`conf`	Attentive Semantic Alignment with Offset-Aware Correlation Kernels. ECCV (4) Paul Hongsuck Seo, Jongmin Lee, Deunsol Jung, Bohyung Han, Minsu Cho
2018	J	`jnl`	Attentive Semantic Alignment with Offset-Aware Correlation Kernels. CoRR Paul Hongsuck Seo, Jongmin Lee, Deunsol Jung, Bohyung Han, Minsu Cho
2018	—	`conf`	CPlaNet: Enhancing Image Geolocalization by Combinatorial Partitioning of Maps. ECCV (10) Paul Hongsuck Seo, Tobias Weyand, Jack Sim, Bohyung Han
2018	J	`jnl`	CPlaNet: Enhancing Image Geolocalization by Combinatorial Partitioning of Maps. CoRR Paul Hongsuck Seo, Tobias Weyand, Jack Sim, Bohyung Han
2018	J	`jnl`	Confidence Calibration in Deep Neural Networks through Stochastic Inferences. CoRR Seonguk Seo, Paul Hongsuck Seo, Bohyung Han
2018	A	`conf`	Progressive Attention Networks for Visual Attribute Prediction. BMVC Paul Hongsuck Seo, Zhe Lin, Scott Cohen, Xiaohui Shen, Bohyung Han
2017	A*	`conf`	MarioQA: Answering Questions by Watching Gameplay Videos. ICCV Jonghwan Mun, Paul Hongsuck Seo, Ilchae Jung, Bohyung Han
2017	—	`conf`	Visual Reference Resolution using Attention Memory for Visual Dialog. NIPS Paul Hongsuck Seo, Andreas M. Lehrmann, Bohyung Han, Leonid Sigal
2017	J	`jnl`	Visual Reference Resolution using Attention Memory for Visual Dialog. CoRR Paul Hongsuck Seo, Andreas M. Lehrmann, Bohyung Han, Leonid Sigal
2016	J	`jnl`	Hierarchical Attention Networks. CoRR Paul Hongsuck Seo, Zhe Lin, Scott Cohen, Xiaohui Shen, Bohyung Han
2016	A*	`conf`	Image Question Answering Using Convolutional Neural Network with Dynamic Parameter Prediction. CVPR Hyeonwoo Noh, Paul Hongsuck Seo, Bohyung Han
2016	J	`jnl`	MarioQA: Answering Questions by Watching Gameplay Videos. CoRR Jonghwan Mun, Paul Hongsuck Seo, Ilchae Jung, Bohyung Han
2015	—	`conf`	Conversational Knowledge Teaching Agent that uses a Knowledge Base. SIGDIAL Conference Kyusong Lee, Paul Hongsuck Seo, Junhwi Choi, Sangjun Koo, Gary Geunbae Lee
2015	J	`jnl`	Image Question Answering using Convolutional Neural Network with Dynamic Parameter Prediction. CoRR Hyeonwoo Noh, Paul Hongsuck Seo, Bohyung Han

Nicolò Altamura is a security engineer and computer science researcher specializing in software protection, reverse engineering, program analysis, and binary deobfuscation. He holds a master's degree in Computer Science and Engineering from the University of Verona, graduating with honors, and works at emproof, focusing on software protection and the challenges of analyzing and understanding compiled software.

His research explores the relationship between program analysis and code obfuscation, with particular emphasis on how software transformations affect the ability of automated tools to recover program behavior. His interests span static analysis, binary analysis, decompilation, reverse engineering, and techniques for analyzing and simplifying obfuscated code.

Beyond academic research, Nicolò develops and contributes to tools for reverse engineering and software analysis. His projects include obfuscation_analysis, a Binary Ninja plugin for analyzing and simplifying obfuscated code; Pocket, an obfuscator for mixed Boolean-arithmetic expressions; and ptxNinja, a tool for reverse engineering NVIDIA GPU code represented in the PTX virtual instruction set.

His research also extends to binary datasets and software evolution. In 2026, he co-authored ASSEMBLAGE-DEEPHISTORY: A Cross-Build Binary Dataset with Temporal Coverage, a research work addressing the availability of binary data across multiple software builds and points in time, supporting research into binary analysis and changes between program versions.

Across his research, engineering work, and open-source contributions, Nicolò focuses on advancing the understanding, analysis, and protection of software against increasingly sophisticated obfuscation and reverse-engineering challenges.

Nicolò Altamura is not a football player. Please avoid reporting this kind of infromation.