ICCV 2017
at
Experts in computer vision around the world gathered in Venice last week for the International Conference on Computer Vision, a biannual premier event in the field lasting over a week and packed with papers, posters and workshops. NAVER LABS Europe was proud to have several papers, posters and invited talks during the week. Below is a list of our presentations and other contributions to the event with the odd photo!
Main Conference papers
Joint learning of object and action detectors, Vicky Kalogeiton (INRIA, Univ. Edinburgh), Philippe Weinzaepfel (NAVER LABS Europe), Cordelia Schmid (INRIA) and Vittorio Ferrari (Univ. of Edinburgh). Full paper-PDF
Abstract: While most existing approaches for de tection in videos focus on objects or human actions separately, we aim at jointly detecting objects performing actions, such as cat eating or dog jumping. We introduce an end-to-end multitask objective that jointly learns object-action relationships. We compare it with different training objectives, validate its effectiveness for detecting objects-actions in videos, and show that both tasks of object and action detection bene- fit from this joint learning. Moreover, the proposed architecture can be used for zero-shot learning of actions: our multitask objective leverages the commonalities of an action performed by different objects, e.g. dog and cat jumping, enabling to detect actions of an object without training with these object-actions pairs. In experiments on the A2D dataset, we obtain state-of-the-art results on segmentation of object-action pairs. We finally apply our multitask architecture to detect visual relationships between objects in images of the VRD dataset
Action Tubelet Detector for Spatio-Temporal Action Localization, Vicky Kalogeiton (INRIA and Univ. of Edinburgh), Philippe Weinzaepfel (NAVER LABS Europe), Cordelia Schmid (INRIA) and Vittorio Ferrari (Univ. of Edinburgh). Full paper PDF
Abstract: Current state-of-the-art approaches for spatio-temporal action localization rely on detections at the frame level that are then linked or tracked across time. In this paper, we leverage the temporal continuity of videos instead of operating at the frame level. We propose the ACtion Tubelet detector (ACT-detector) that takes as input a sequence of frames and outputs tubelets, i.e., sequences of bounding boxes with associated scores. The same way state-of-the art object detectors rely on anchor boxes, our ACT-detector is based on anchor cuboids. We build upon the SSD framework [18]. Convolutional features are extracted for each frame, while scores and regressions are based on the temporal stacking of these features, thus exploiting information from a sequence. Our experimental results show that leveraging sequences of frames significantly improves detection performance over using individual frames. The gain of our tubelet detector can be explained by both more accurate scores and more precise localization. Our ACT-detector outperforms the state-of-the-art methods for frame-mAP and video-mAP on the J-HMDB [12] and UCF-101 [30] datasets, in particular at high overlap thresholds.
David Novotny presenting
Learning 3D Object Categories by Looking Around Them, David Novotny (Univ. of Oxford and NAVER LABS Europe), Diane Larlus and Andrea Vedaldi (Univ. of Oxford). Oral. (Full paper PDF)
Abstract: Traditional approaches for learning 3D object categories use either synthetic data or manual supervision. In this paper, we propose a method which does not require manual annotations and is instead cued by observing objects from a moving vantage point. Our system builds on two innovations: a Siamese viewpoint factorization network that robustly aligns different videos together without explicitly comparing 3D shapes; and a 3D shape completion network that can extract the full shape of an object from partial observations. We also demonstrate the benefits of configuring networks to perform probabilistic predictions as well as of geometry-aware data augmentation schemes. We obtain state-of-the-art results on publicly-available benchmarks.
Gabriela autographing her book, thank you @dimadamen for the photo
Invited workshop talks:
- Diane Larlus on Beyond Instance-Level Image Retrieval: Leveraging Captions to Learn a Global Visual Representation for Semantic Retrieval, 5th Workshop on Web-scale Vision and Social Media (VSM).
- Gabriela Csurka on ‘Domain Adaptation for Visual Applications’ at TASK-CV, Transferring and Adapting Source Knowledge in Computer Vision. Gabriela was caught autographing the book she just edited on the topic available from Springer Domain Adaptation in Computer Vision Applications, ed. Gabriela Csurka and published by Springer, DOI: 10.1007/978-3-319-58347-1_14: University of Oxford, UK.
Workshop spotlight presentation
Discrepancy-based networks for unsupervised domain adaptation: a comparative study, Gabriela Csurka, Fabien Baradel (INSA-LIRIS), Boris Chidlovskii and Stephane Clinchant, TASK-CV, Full paper – PDF
VisDa2017 2nd: NAVER LABS Europe
NAVER LABS Europe was 2nd in the Visual Domain Adaptation (VisDA2017) Classification Challenge of TASK-CV. Boris Chidlovskii presented our methods at the workshop.
Maxime Bucher – Best Paper Award
NAVER LABS sponsored the best paper at the TASK-CV Workshop (Transferring and Adapting Source Knowledge in Computer Vision).
Congratulations go to Maxime Bucher, Stephane Herbin and Frederic Jurie for their paper “Generating Visual Representations for Zero-Shot Classification”
To make robots autonomous in real-world everyday spaces, they should be able to learn from their interactions within these spaces, how to best execute tasks specified by non-expert users in a safe and reliable way. To do so requires sequential decision-making skills that combine machine learning, adaptive planning and control in uncertain environments as well as solving hard combinatorial optimisation problems. Our research combines expertise in reinforcement learning, computer vision, robotic control, sim2real transfer, large multimodal foundation models and neural combinatorial optimisation to build AI-based architectures and algorithms to improve robot autonomy and robustness when completing everyday complex tasks in constantly changing environments.
VISION
The research we conduct on expressive visual representations is applicable to visual search, object detection, image classification and the automatic extraction of 3D human poses and shapes that can be used for human behavior understanding and prediction, human-robot interaction or even avatar animation. We also extract 3D information from images that can be used for intelligent robot navigation, augmented reality and the 3D reconstruction of objects, buildings or even entire cities.
Our work covers the spectrum from unsupervised to supervised approaches, and from very deep architectures to very compact ones. We’re excited about the promise of big data to bring big performance gains to our algorithms but also passionate about the challenge of working in data-scarce and low-power scenarios.
Furthermore, we believe that a modern computer vision system needs to be able to continuously adapt itself to its environment and to improve itself via lifelong learning. Our driving goal is to use our research to deliver embodied intelligence to our users in robotics, autonomous driving, via phone cameras and any other visual means to reach people wherever they may be.
This web site uses cookies for the site search, to display videos and for aggregate site analytics.
Learn more about these cookies in our privacy notice.
Cookie settings
You may choose which kind of cookies you allow when visiting this website. Click on "Save cookie settings" to apply your choice.
This content is currently blocked. To view the content please either 'Accept social media cookies' or 'Accept all cookies'.
For more information on cookies see our privacy notice.