Laura Sevilla-Lara

18 papers · 2016–2026 · 6 conferences · across top CS/AI conferences

Achievements

🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌈 Renaissance Researcher (5) 🗺️ Taxonomy Completionist (48) 🐣 Hot Topic Early Bird 🌍 Conference Polyglot (6) 🏃 Academic Marathon (10) 🐝 Cross-Pollinator (6) 💎 Century Club (17) 🔥 Unstoppable (8) 🗃️ Keyword Collector (76)

Conferences

CVPR (7) AAAI (3) ECCV (3) ICCV (2) WACV (2) ACL (1)

Top co-authors

Marcus Rohrbach (6) Gen Li (6) Frank Keller (5) Varun Jampani (4) Shreyank N Gowda (4) Deqing Sun (4) Matt Feiszli (2) Anil Batra (2) Michael J. Black (2) Zhicheng Yan (2)

Keywords

video understanding (6) action recognition (4) optical flow (3) semantic segmentation (3) computational efficiency (3) motion estimation (3) video classification (2) prototype learning (2) few-shot learning (2) scene understanding (2) temporal modeling (2) affordance learning (2) computer vision (2) object detection (1) representation learning (1) structure from motion (1) image segmentation (1) facial animation (1) transformer efficiency (1) token selection (1)

Papers

Mask2IV: Interaction-Centric Video Generation via Mask Trajectories AAAI 2026

GaussianHeadTalk: Wobble-Free 3D Talking Heads with Audio Driven Gaussian Splatting WACV 2026

Learning Precise Affordances from Egocentric Videos for Robotic Manipulation ICCV 2025

Predicting Implicit Arguments in Procedural Video Instructions ACL 2025

Principles of Visual Tokens for Efficient Video Understanding ICCV 2025

One-Shot Open Affordance Learning with Foundation Models CVPR 2024

Efficient Pre-training for Localized Instruction Generation of Procedural Videos ECCV 2024

Learning Action Changes by Measuring Verb-Adverb Textual Relationships CVPR 2023

LOCATE: Localize and Transfer Object Parts for Weakly Supervised Affordance Grounding CVPR 2023

Learn2Augment: Learning to Composite Videos for Data Augmentation in Action Recognition ECCV 2022

CLASTER: Clustering with Reinforcement Learning for Zero-Shot Action Recognition ECCV 2022

Adaptive Prototype Learning and Allocation for Few-Shot Segmentation CVPR 2021

SMART Frame Selection for Action Recognition AAAI 2021

Only Time Can Tell: Discovering Temporal Data for Temporal Modeling WACV 2021

FASTER Recurrent Networks for Efficient Video Classification AAAI 2020

DMC-Net: Generating Discriminative Motion Cues for Fast Compressed Video Action Recognition CVPR 2019

Optical Flow in Mostly Rigid Scenes CVPR 2017

Optical Flow With Semantic Segmentation and Localized Layers CVPR 2016