Juan-Manuel Pérez-Rúa

51 papers A* 12A 5B 2Journal 31

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Faster Diffusion Through Temporal Attention Decomposition. Trans. Mach. Learn. Res. Haozhe Liu, Wentian Zhang, Jinheng Xie, Francesco Faccio, Mengmeng Xu, Tao Xiang, Mike Zheng Shou, Juan-Manuel Pérez-Rúa, Jürgen Schmidhuber
2025	J	`jnl`	HiStream: Efficient High-Resolution Video Generation via Redundancy-Eliminated Streaming. CoRR Haonan Qiu, Shikun Liu, Zijian Zhou, Zhaochong An, Weiming Ren, Zhiheng Liu, Jonas Schult, Sen He, Shoufa Chen, Yuren Cong, Tao Xiang, Ziwei Liu, Juan-Manuel Pérez-Rúa
2025	A*	`conf`	Learning Flow Fields in Attention for Controllable Person Image Generation. CVPR Zijian Zhou, Shikun Liu, Xiao Han, Haozhe Liu, Kam Woh Ng, Tian Xie, Yuren Cong, Hang Li, Mengmeng Xu, Juan-Manuel Pérez-Rúa, Aditya Patel, Tao Xiang, Miaojing Shi, Sen He
2025	J	`jnl`	MarDini: Masked Auto-regressive Diffusion for Video Generation at Scale. Trans. Mach. Learn. Res. Haozhe Liu, Shikun Liu, Zijian Zhou, Mengmeng Xu, Yanping Xie, Xiao Han, Juan Camilo Pérez, Ding Liu, Kumara Kahatapitiya, Menglin Jia, Jui-Chieh Wu, Sen He, Tao Xiang, Jürgen Schmidhuber, Juan-Manuel Pérez-Rúa
2025	J	`jnl`	Mixture of States: Routing Token-Level Dynamics for Multimodal Generation. CoRR Haozhe Liu, Ding Liu, Mingchen Zhuge, Zijian Zhou, Tian Xie, Sen He, Yukang Yang, Shuming Liu, Yuren Cong, Jiadong Guo, Hongyu Xu, Ke Xu, Kam Woh Ng, Juan C. Pérez, Juan-Manuel Pérez-Rúa, Tao Xiang, Wei Liu, Shikun Liu, Jürgen Schmidhuber
2025	J	`jnl`	Scaling Sequence-to-Sequence Generative Neural Rendering. CoRR Shikun Liu, Kam Woh Ng, Wonbong Jang, Jiadong Guo, Junlin Han, Haozhe Liu, Yiannis Douratsos, Juan C. Pérez, Zijian Zhou, Chi Phung, Tao Xiang, Juan-Manuel Pérez-Rúa
2025	J	`jnl`	TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models. CoRR Zhiheng Liu, Weiming Ren, Haozhe Liu, Zijian Zhou, Shoufa Chen, Haonan Qiu, Xiaoke Huang, Zhaochong An, Fanny Yang, Aditya Patel, Viktar Atliha, Tony Ng, Xiao Han, Chuyan Zhu, Chenyang Zhang, Ding Liu, Juan-Manuel Pérez-Rúa, Sen He, Jürgen Schmidhuber, Wenhu Chen, Ping Luo, Wei Liu, Tao Xiang, Jonas Schult, Yuren Cong
2024	A*	`conf`	Boundary Denoising for Video Activity Localization. ICLR Mengmeng Xu, Mattia Soldan, Jialin Gao, Shuming Liu, Juan-Manuel Pérez-Rúa, Bernard Ghanem
2024	A*	`conf`	FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing. ICLR Yuren Cong, Mengmeng Xu, Christian Simon, Shoufa Chen, Jiawei Ren, Yanping Xie, Juan-Manuel Pérez-Rúa, Bodo Rosenhahn, Tao Xiang, Sen He
2024	A*	`conf`	GenTron: Diffusion Transformers for Image and Video Generation. CVPR Shoufa Chen, Mengmeng Xu, Jiawei Ren, Yuren Cong, Sen He, Yanping Xie, Animesh Sinha, Ping Luo, Tao Xiang, Juan-Manuel Pérez-Rúa
2024	J	`jnl`	Learning Flow Fields in Attention for Controllable Person Image Generation. CoRR Zijian Zhou, Shikun Liu, Xiao Han, Haozhe Liu, Kam Woh Ng, Tian Xie, Yuren Cong, Hang Li, Mengmeng Xu, Juan-Manuel Pérez-Rúa, Aditya Patel, Tao Xiang, Miaojing Shi, Sen He
2024	J	`jnl`	MarDini: Masked Autoregressive Diffusion for Video Generation at Scale. CoRR Haozhe Liu, Shikun Liu, Zijian Zhou, Mengmeng Xu, Yanping Xie, Xiao Han, Juan C. Pérez, Ding Liu, Kumara Kahatapitiya, Menglin Jia, Jui-Chieh Wu, Sen He, Tao Xiang, Jürgen Schmidhuber, Juan-Manuel Pérez-Rúa
2023	J	`jnl`	Boundary-Denoising for Video Activity Localization. CoRR Mengmeng Xu, Mattia Soldan, Jialin Gao, Shuming Liu, Juan-Manuel Pérez-Rúa, Bernard Ghanem
2023	J	`jnl`	FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing. CoRR Yuren Cong, Mengmeng Xu, Christian Simon, Shoufa Chen, Jiawei Ren, Yanping Xie, Juan-Manuel Pérez-Rúa, Bodo Rosenhahn, Tao Xiang, Sen He
2023	J	`jnl`	GenTron: Delving Deep into Diffusion Transformers for Image and Video Generation. CoRR Shoufa Chen, Mengmeng Xu, Jiawei Ren, Yuren Cong, Sen He, Yanping Xie, Animesh Sinha, Ping Luo, Tao Xiang, Juan-Manuel Pérez-Rúa
2023	J	`jnl`	Hyper-VolTran: Fast and Generalizable One-Shot Image to 3D Object Structure via HyperNetworks. CoRR Christian Simon, Sen He, Juan-Manuel Pérez-Rúa, Mengmeng Xu, Amine Benhalloum, Tao Xiang
2023	A*	`conf`	Where is my Wallet? Modeling Object Proposal Sets for Egocentric Visual Query Localization. CVPR Mengmeng Xu, Yanghao Li, Cheng-Yang Fu, Bernard Ghanem, Tao Xiang, Juan-Manuel Pérez-Rúa
2022	J	`jnl`	Multi-Modal Few-Shot Temporal Action Detection via Vision-Language Meta-Adaptation. CoRR Sauradip Nag, Mengmeng Xu, Xiatian Zhu, Juan-Manuel Pérez-Rúa, Bernard Ghanem, Yi-Zhe Song, Tao Xiang
2022	J	`jnl`	Negative Frames Matter in Egocentric Visual Query 2D Localization. CoRR Mengmeng Xu, Cheng-Yang Fu, Yanghao Li, Bernard Ghanem, Juan-Manuel Pérez-Rúa, Tao Xiang
2022	J	`jnl`	Where is my Wallet? Modeling Object Proposal Sets for Egocentric Visual Query Localization. CoRR Mengmeng Xu, Yanghao Li, Cheng-Yang Fu, Bernard Ghanem, Tao Xiang, Juan-Manuel Pérez-Rúa
2021	A*	`conf`	Boundary-sensitive Pre-training for Temporal Localization in Videos. ICCV Mengmeng Xu, Juan-Manuel Pérez-Rúa, Victor Escorcia, Brais Martínez, Xiatian Zhu, Li Zhang, Bernard Ghanem, Tao Xiang
2021	A	`conf`	Few-shot Action Recognition with Prototype-centered Attentive Learning. BMVC Xiatian Zhu, Antoine Toisoul, Juan-Manuel Pérez-Rúa, Li Zhang, Brais Martínez, Tao Xiang
2021	J	`jnl`	Few-shot Action Recognition with Prototype-centered Attentive Learning. CoRR Xiatian Zhu, Antoine Toisoul, Juan-Manuel Pérez-Rúa, Li Zhang, Brais Martínez, Tao Xiang
2021	A	`conf`	Knowing What, Where and When to Look: Video Action modelling with Attention. BMVC Juan-Manuel Pérez-Rúa, Brais Martínez, Xiatian Zhu, Antoine Toisoul, Victor Escorcia, Tao Xiang
2021	J	`jnl`	Low-Fidelity End-to-End Video Encoder Pre-training for Temporal Action Localization. CoRR Mengmeng Xu, Juan-Manuel Pérez-Rúa, Xiatian Zhu, Bernard Ghanem, Brais Martínez
2021	A*	`conf`	Low-Fidelity Video Encoder Optimization for Temporal Action Localization. NeurIPS Mengmeng Xu, Juan-Manuel Pérez-Rúa, Xiatian Zhu, Bernard Ghanem, Brais Martínez
2021	J	`jnl`	SAIC_Cambridge-HuPBA-FBK Submission to the EPIC-Kitchens-100 Action Recognition Challenge 2021. CoRR Swathikiran Sudhakaran, Adrian Bulat, Juan-Manuel Pérez-Rúa, Alex Falcon, Sergio Escalera, Oswald Lanz, Brais Martínez, Georgios Tzimiropoulos
2021	A*	`conf`	Space-time Mixing Attention for Video Transformer. NeurIPS Adrian Bulat, Juan-Manuel Pérez-Rúa, Swathikiran Sudhakaran, Brais Martínez, Georgios Tzimiropoulos
2021	J	`jnl`	Space-time Mixing Attention for Video Transformer. CoRR Adrian Bulat, Juan-Manuel Pérez-Rúa, Swathikiran Sudhakaran, Brais Martínez, Georgios Tzimiropoulos
2021	A	`conf`	TNT: Text-Conditioned Network with Transductive Inference for Few-Shot Video Classification. BMVC Andrés Villa, Juan-Manuel Pérez-Rúa, Vladimir Araujo, Juan Carlos Niebles, Victor Escorcia, Alvaro Soto
2021	J	`jnl`	TNT: Text-Conditioned Network with Transductive Inference for Few-Shot Video Classification. CoRR Andrés Villa, Juan-Manuel Pérez-Rúa, Vladimir Araujo, Juan Carlos Niebles, Victor Escorcia, Alvaro Soto
2020	J	`jnl`	Boundary-sensitive Pre-training for Temporal Localization in Videos. CoRR Mengmeng Xu, Juan-Manuel Pérez-Rúa, Victor Escorcia, Brais Martínez, Xiatian Zhu, Li Zhang, Bernard Ghanem, Tao Xiang
2020	J	`jnl`	Egocentric Action Recognition by Video Attention and Temporal Context. CoRR Juan-Manuel Pérez-Rúa, Antoine Toisoul, Brais Martínez, Victor Escorcia, Li Zhang, Xiatian Zhu, Tao Xiang
2020	A*	`conf`	Incremental Few-Shot Object Detection. CVPR Juan-Manuel Pérez-Rúa, Xiatian Zhu, Timothy M. Hospedales, Tao Xiang
2020	J	`jnl`	Incremental Few-Shot Object Detection. CoRR Juan-Manuel Pérez-Rúa, Xiatian Zhu, Timothy M. Hospedales, Tao Xiang
2020	J	`jnl`	Knowing What, Where and When to Look: Efficient Video Action Modeling with Attention. CoRR Juan-Manuel Pérez-Rúa, Brais Martínez, Xiatian Zhu, Antoine Toisoul, Victor Escorcia, Tao Xiang
2020	J	`jnl`	ROAM: A Rich Object Appearance Model with Application to Rotoscoping. IEEE Trans. Pattern Anal. Mach. Intell. Juan-Manuel Pérez-Rúa, Ondrej Miksik, Tomás Crivelli, Patrick Bouthemy, Philip H. S. Torr, Patrick Pérez
2019	A*	`conf`	MFAS: Multimodal Fusion Architecture Search. CVPR Juan-Manuel Pérez-Rúa, Valentin Vielzeuf, Stéphane Pateux, Moez Baccouche, Frédéric Jurie
2019	J	`jnl`	MFAS: Multimodal Fusion Architecture Search. CoRR Juan-Manuel Pérez-Rúa, Valentin Vielzeuf, Stéphane Pateux, Moez Baccouche, Frédéric Jurie
2018	A	`conf`	Efficient Progressive Neural Architecture Search. BMVC Juan-Manuel Pérez-Rúa, Moez Baccouche, Stéphane Pateux
2018	J	`jnl`	Efficient Progressive Neural Architecture Search. CoRR Juan-Manuel Pérez-Rúa, Moez Baccouche, Stéphane Pateux
2018	J	`jnl`	Learning how to be robust: Deep polynomial regression. CoRR Juan-Manuel Pérez-Rúa, Tomás Crivelli, Patrick Bouthemy, Patrick Pérez
2017	J	`jnl`	Detection and Localization of Anomalous Motion in Video Sequences from Local Histograms of Labeled Affine Flows. Frontiers ICT Juan-Manuel Pérez-Rúa, Antoine Basset, Patrick Bouthemy
2017	—	`—`	Hierarchical motion-based video analysis with applications to video post-production. (Analyse de vidéo par décomposition hiérarchique du mouvement appliquée à la post-production vidéo). Juan-Manuel Pérez-Rúa
2017	A*	`conf`	ROAM: A Rich Object Appearance Model with Application to Rotoscoping. CVPR Ondrej Miksik, Juan-Manuel Pérez-Rúa, Philip H. S. Torr, Patrick Pérez
2016	A*	`conf`	Determining Occlusions from Space and Time Image Reconstructions. CVPR Juan-Manuel Pérez-Rúa, Tomás Crivelli, Patrick Bouthemy, Patrick Pérez
2016	A	`conf`	Discovering motion hierarchies via tree-structured coding of trajectories. BMVC Juan-Manuel Pérez-Rúa, Tomás Crivelli, Patrick Pérez, Patrick Bouthemy
2016	B	`conf`	Hierarchical motion decomposition for dynamic scene parsing. ICIP Juan-Manuel Pérez-Rúa, Tomás Crivelli, Patrick Pérez, Patrick Bouthemy
2016	J	`jnl`	Object-guided motion estimation. Comput. Vis. Image Underst. Juan-Manuel Pérez-Rúa, Tomás Crivelli, Patrick Pérez
2016	J	`jnl`	ROAM: a Rich Object Appearance Model with Application to Rotoscoping. CoRR Ondrej Miksik, Juan-Manuel Pérez-Rúa, Philip H. S. Torr, Patrick Pérez
2015	B	`conf`	Background-foreground tracking for video object segmentation. ICIP Juan-Manuel Pérez-Rúa, Tomás Crivelli, Patrick Pérez