JP
Juan-Manuel Perez-Rua
cs.CVcs.AIcs.LGcs.MMcs.CLcs.NE
On Valency
published · living versionsW_mv8ghxt6·v1 · currentpublished
OverSeer: Multi-Agent World Models Beyond What Agents See
with Runjia Li, Kam Woh Ng, Minghao Chen, Junlin Han +4
1 version
Preprints & journals
29 papers in the corpus · 2018–2026OverSeer: Multi-Agent World Models Beyond What Agents See2610.28554v1 · Runjia Li, Kam Woh Ng, Minghao Chen et al.2026 · 0 citationsarXivon Valency
In-Flight KV Cache with Clean Anchors for Faster Autoregressive Video Diffusion2609.32540v2 · Yikai Wang, Xiao Han, Mengmeng Xu et al.2026 · 0 citationsarXiv
Rays as Pixels: Learning A Joint Distribution of Videos and Camera Trajectories2604.09429v4 · Wonbong Jang, Shikun Liu, Soubhik Sanyal et al.2026 · 0 citationsarXiv
HiStream: Efficient High-Resolution Video Generation via Redundancy-Eliminated Streaming2512.21338v2 · Haonan Qiu, Shikun Liu, Zijian Zhou et al.2025 · 0 citationsarXiv
TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models2512.02014v1 · Zhiheng Liu, Weiming Ren, Haozhe Liu et al.2025 · 0 citationsarXiv
Mixture of States: Routing Token-Level Dynamics for Multimodal Generation2511.12207v2 · Haozhe Liu, Ding Liu, Mingchen Zhuge et al.2025 · 0 citationsarXiv
Scaling Sequence-to-Sequence Generative Neural Rendering2510.04236v3 · Shikun Liu, Kam Woh Ng, Wonbong Jang et al.2025 · 0 citationsarXiv
Learning Flow Fields in Attention for Controllable Person Image Generation2412.08486v2 · Zijian Zhou, Shikun Liu, Xiao Han et al.2024 · 14 citationsarXiv
MarDini: Masked Autoregressive Diffusion for Video Generation at Scale2410.20280v1 · Haozhe Liu, Shikun Liu, Zijian Zhou et al.2024 · 1 citationarXiv
Hyper-VolTran: Fast and Generalizable One-Shot Image to 3D Object Structure via HyperNetworks2312.16218v2 · Christian Simon, Sen He, Juan-Manuel Perez-Rua et al.2023 · 0 citationsarXiv
GenTron: Diffusion Transformers for Image and Video Generation2312.04557v2 · Shoufa Chen, Mengmeng Xu, Jiawei Ren et al.2023 · 44 citationsarXiv
FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing2310.05922v3 · Yuren Cong, Mengmeng Xu, Christian Simon et al.2023 · 15 citationsarXiv
Boundary-Denoising for Video Activity Localization2304.02934v1 · Mengmeng Xu, Mattia Soldan, Jialin Gao et al.2023 · 6 citationsarXiv
Multi-Modal Few-Shot Temporal Action Detection2211.14905v2 · Sauradip Nag, Mengmeng Xu, Xiatian Zhu et al.2022 · 1 citationarXiv
Where is my Wallet? Modeling Object Proposal Sets for Egocentric Visual Query Localization2211.10528v2 · Mengmeng Xu, Yanghao Li, Cheng-Yang Fu et al.2022 · 9 citationsarXiv
Negative Frames Matter in Egocentric Visual Query 2D Localization2208.01949v1 · Mengmeng Xu, Cheng-Yang Fu, Yanghao Li et al.2022 · 4 citationsarXiv
Sylph: A Hypernetwork Framework for Incremental Few-shot Object Detection2203.13903v2 · Li Yin, Juan M Perez-Rua, Kevin J Liang2022 · 56 citationsarXiv
SAIC_Cambridge-HuPBA-FBK Submission to the EPIC-Kitchens-100 Action Recognition Challenge 20212110.02902v1 · Swathikiran Sudhakaran, Adrian Bulat, Juan-Manuel Perez-Rua et al.2021 · 0 citationsarXiv
TNT: Text-Conditioned Network with Transductive Inference for Few-Shot Video Classification2106.11173v2 · Andr'es Villa, Juan-Manuel Perez-Rua, Victor Escorcia et al.2021 · 0 citationsarXiv
Space-time Mixing Attention for Video Transformer2106.05968v2 · Adrian Bulat, Juan-Manuel Perez-Rua, Swathikiran Sudhakaran et al.2021 · 79 citationsarXiv
Low-Fidelity End-to-End Video Encoder Pre-training for Temporal Action Localization2103.15233v3 · Mengmeng Xu, Juan-Manuel Perez-Rua, Xiatian Zhu et al.2021 · 6 citationsarXiv
Few-shot Action Recognition with Prototype-centered Attentive Learning2101.08085v4 · Xiatian Zhu, Antoine Toisoul, Juan-Manuel Perez-Rua et al.2021 · 49 citationsBMVC 2021
Boundary-sensitive Pre-training for Temporal Localization in Videos2011.10830v3 · Mengmeng Xu, Juan-Manuel Perez-Rua, Victor Escorcia et al.2020 · 53 citationsarXiv
Egocentric Action Recognition by Video Attention and Temporal Context2007.01883v1 · Juan-Manuel Perez-Rua, Antoine Toisoul, Brais Martinez et al.2020 · 1 citationarXiv
Knowing What, Where and When to Look: Efficient Video Action Modeling with Attention2004.01278v1 · Juan-Manuel Perez-Rua, Brais Martinez, Xiatian Zhu et al.2020 · 17 citationsarXiv
Incremental Few-Shot Object Detection2003.04668v2 · Juan-Manuel Perez-Rua, Xiatian Zhu, Timothy Hospedales et al.2020 · 55 citationsarXiv
MFAS: Multimodal Fusion Architecture Search1903.06496v1 · Juan-Manuel P'erez-R'ua, Valentin Vielzeuf, St'ephane Pateux et al.2019 · 193 citationsarXiv
Efficient Progressive Neural Architecture Search1808.00391v1 · Juan-Manuel Perez-Rua, Moez Baccouche, Stephane Pateux2018 · 35 citationsarXiv
Learning how to be robust: Deep polynomial regression1804.06504v2 · Juan-Manuel Perez-Rua, Tomas Crivelli, Patrick Bouthemy et al.2018 · 3 citationsarXiv
Career total: 37 works. 29 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.