Picture for Josef Sivic

Josef Sivic

Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning

Mar 21, 2023
Antoine Yang, Arsha Nagrani, Paul Hongsuck Seo, Antoine Miech, Jordi Pont-Tuset, Ivan Laptev, Josef Sivic, Cordelia Schmid

Figure 1 for Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning

Figure 2 for Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning

Figure 3 for Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning

Figure 4 for Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning

* CVPR 2023 Camera-Ready; Project Webpage: https://antoyang.github.io/vid2seq.html ; 18 pages; 6 figures

Access Paper or Ask Questions

Benchmarking Learning Efficiency in Deep Reservoir Computing

Sep 29, 2022
Hugo Cisneros, Josef Sivic, Tomas Mikolov

Figure 1 for Benchmarking Learning Efficiency in Deep Reservoir Computing

Figure 2 for Benchmarking Learning Efficiency in Deep Reservoir Computing

Figure 3 for Benchmarking Learning Efficiency in Deep Reservoir Computing

Figure 4 for Benchmarking Learning Efficiency in Deep Reservoir Computing

* Conference on Lifelong Learning Agents, Aug 2022, Montreal, Canada

Access Paper or Ask Questions

Differentiable Collision Detection: a Randomized Smoothing Approach

Sep 19, 2022
Louis Montaut, Quentin Le Lidec, Antoine Bambade, Vladimir Petrik, Josef Sivic, Justin Carpentier

Figure 1 for Differentiable Collision Detection: a Randomized Smoothing Approach

Figure 2 for Differentiable Collision Detection: a Randomized Smoothing Approach

Figure 3 for Differentiable Collision Detection: a Randomized Smoothing Approach

Figure 4 for Differentiable Collision Detection: a Randomized Smoothing Approach

* 7 pages, 6 figures, 2 tables

Access Paper or Ask Questions

Zero-Shot Video Question Answering via Frozen Bidirectional Language Models

Jun 16, 2022
Antoine Yang, Antoine Miech, Josef Sivic, Ivan Laptev, Cordelia Schmid

Figure 1 for Zero-Shot Video Question Answering via Frozen Bidirectional Language Models

Figure 2 for Zero-Shot Video Question Answering via Frozen Bidirectional Language Models

Figure 3 for Zero-Shot Video Question Answering via Frozen Bidirectional Language Models

Figure 4 for Zero-Shot Video Question Answering via Frozen Bidirectional Language Models

* 23 pages; 5 figures

Access Paper or Ask Questions

Collision Detection Accelerated: An Optimization Perspective

May 20, 2022
Louis Montaut, Quentin Le Lidec, Vladimir Petrik, Josef Sivic, Justin Carpentier

Figure 1 for Collision Detection Accelerated: An Optimization Perspective

Figure 2 for Collision Detection Accelerated: An Optimization Perspective

Figure 3 for Collision Detection Accelerated: An Optimization Perspective

Figure 4 for Collision Detection Accelerated: An Optimization Perspective

* Robotics: Science and Systems 2022
* RSS 2022, 12 pages, 9 figures, 2 tables

Access Paper or Ask Questions