Victor Escorcia — accepted AI-conference papers

2025

Edge-SD-SR: Low Latency and Parameter Efficient On-device Super-Resolution with Stable Diffusion via Bidirectional Conditioning

Isma Hadji, Mehdi Noroozi, Victor Escorcia, Anestis Zaganidis, Brais Martinez, Georgios Tzimiropoulos

CVPR 2025poster

There has been immense progress recently in the visual quality of Stable Diffusion-based Super Resolution (SD-SR). However, deploying large diffusion models on computationally restricted devices such as mobile phones remains impractical due to the large model size and high latency. This is compounde…

Cited by 0 Source ↗PDF ↗Scholar ↗

2022

SOS! Self-Supervised Learning over Sets of Handled Objects in Egocentric Action Recognition

Victor Escorcia, Ricardo Guerrero, Xiatian Zhu, Brais Martinez

ECCV 2022poster

"Learning an egocentric action recognition model from video data is challenging due to distractors in the background, e.g., irrelevant objects. Further integrating object information into an action model is hence beneficial. Existing methods often leverage a generic object detector to identify and r…

Cited by 11 Source ↗PDF ↗Scholar ↗

2022

vCLIMB: A Novel Video Class Incremental Learning Benchmark

Andrés Villa, Kumail Alhamoud, Victor Escorcia, Fabian Caba, Juan León Alcázar, Bernard Ghanem

CVPR 2022oral

Continual learning (CL) is under-explored in the video domain. The few existing works contain splits with imbalanced class distributions over the tasks, or study the problem in unsuitable datasets. We introduce vCLIMB, a novel video continual learning benchmark. vCLIMB is a standardized test-bed to…

Cited by 46 PDF ↗Scholar ↗

2021

Boundary-Sensitive Pre-Training for Temporal Localization in Videos

Mengmeng Xu, Juan-Manuel Pérez-Rúa, Victor Escorcia, Brais Martínez, Xiatian Zhu, Li Zhang +2

ICCV 2021poster

Many video analysis tasks require temporal localization for the detection of content changes. However, most existing models developed for these tasks are pre-trained on general video action classification tasks. This is due to large scale annotation of temporal boundaries in untrimmed videos being e…

Cited by 76 PDF ↗code ↗Scholar ↗

2018

Diagnosing Error in Temporal Action Detectors

Humam Alwassel, Fabian Caba Heilbron, Victor Escorcia, Bernard Ghanem

ECCV 2018poster

Despite the recent progress in video understanding and the continuous rate of improvement in temporal action localization throughout the years, it is still unclear how far (or close?) we are to solving the problem. To this end, we introduce a new diagnostic tool to analyze the performance of tempora…

Cited by 137 Source ↗PDF ↗code ↗Scholar ↗

2017

SCC: Semantic Context Cascade for Efficient Action Detection

Fabian Caba Heilbron, Wayner Barrios, Victor Escorcia, Bernard Ghanem

CVPR 2017poster

Despite the recent advances in large-scale video analysis, action detection remains as one of the most challenging unsolved problems in computer vision. This snag is in part due to the large volume of data that needs to be analyzed to detect actions in videos. Existing approaches have mitigated the…

Cited by 111 PDF ↗Scholar ↗

2017

SST: Single-Stream Temporal Action Proposals

Shyamal Buch, Victor Escorcia, Chuanqi Shen, Bernard Ghanem, Juan Carlos Niebles

CVPR 2017poster

Our paper presents a new approach for temporal detection of human actions in long, untrimmed video sequences. We introduce Single-Stream Temporal Action Proposals (SST), a new effective and efficient deep architecture for the generation of temporal action proposals. Our network can run continuously…

Cited by 544 PDF ↗code ↗Scholar ↗

2015

ActivityNet: A Large-Scale Video Benchmark for Human Activity Understanding

Fabian Caba Heilbron, Victor Escorcia, Bernard Ghanem, Juan Carlos Niebles

CVPR 2015poster

In spite of many dataset efforts for human action recognition, current computer vision algorithms are still severely limited in terms of the variability and complexity of the actions that they can recognize. This is in part due to the simplicity of current benchmarks, which mostly focus on simple ac…

Cited by 3269 Source ↗PDF ↗Scholar ↗

2015

On the Relationship Between Visual Attributes and Convolutional Networks

Victor Escorcia, Juan Carlos Niebles, Bernard Ghanem

CVPR 2015poster

One of the cornerstone principles of deep models is their abstraction capacity, i.e. their ability to learn abstract concepts from `simpler' ones. Through extensive experiments, we characterize the nature of the relationship between abstract concepts (specifically objects in images) learned by popu…

Cited by 123 Source ↗PDF ↗code ↗Scholar ↗