Next
Livestream will start soon!
Livestream has already ended.
Presentation has not been recorded yet!
  • title: Human-Adversarial Visual Question Answering
      0:00 / 0:00
      • Report Issue
      • Settings
      • Playlists
      • Bookmarks
      • Subtitles Off
      • Playback rate
      • Quality
      • Settings
      • Debug information
      • Server sl-yoda-v3-stream-012-alpha.b-cdn.net
      • Subtitles size Medium
      • Bookmarks
      • Server
      • sl-yoda-v3-stream-012-alpha.b-cdn.net
      • sl-yoda-v3-stream-012-beta.b-cdn.net
      • 1338956956.rsc.cdn77.org
      • 1656830687.rsc.cdn77.org
      • Subtitles
      • Off
      • English
      • Playback rate
      • Quality
      • Subtitles size
      • Large
      • Medium
      • Small
      • Mode
      • Video Slideshow
      • Audio Slideshow
      • Slideshow
      • Video
      My playlists
        Bookmarks
          00:00:00
            Human-Adversarial Visual Question Answering
            • Settings
            • Sync diff
            • Quality
            • Settings
            • Server
            • Quality
            • Server

            Human-Adversarial Visual Question Answering

            Dec 6, 2021

            Speakers

            SS

            Sasha Sheng

            Speaker · 0 followers

            AS

            Amanpreet Singh

            Speaker · 1 follower

            VG

            Vedanuj Goswami

            Speaker · 0 followers

            About

            Performance on the most commonly used Visual Question Answering dataset (VQA v2) is starting to approach human accuracy. However, in interacting with state-of-the-art VQA models, it is clear that the problem is far from being solved. In order to stress test VQA models, we benchmark them against human-adversarial examples. Human subjects interact with a state-of-the-art VQA model, and for each image in the dataset, attempt to find a question where the model’s predicted answer is incorrect. We fin…

            Organizer

            N2
            N2

            NeurIPS 2021

            Account · 1.9k followers

            About NeurIPS 2021

            Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.

            Like the format? Trust SlidesLive to capture your next event!

            Professional recording and live streaming, delivered globally.

            Sharing

            Recommended Videos

            Presentations on similar topic, category or speaker

            Unsupervised Resource Allocation with Graph Neural Networks
            19:34

            Unsupervised Resource Allocation with Graph Neural Networks

            Miles Cranmer, …

            N2
            N2
            NeurIPS 2021 3 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Embedding Principle of Loss Landscape of Deep Neural Networks
            11:09

            Embedding Principle of Loss Landscape of Deep Neural Networks

            Yaoyu Zhang, …

            N2
            N2
            NeurIPS 2021 3 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development
            05:21

            Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development

            Kexin Huang, …

            N2
            N2
            NeurIPS 2021 3 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            A new open journal for machine learning
            30:58

            A new open journal for machine learning

            Hugo Larochelle, …

            N2
            N2
            NeurIPS 2021 3 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Width-based Lookaheads with Learnt Base Policies and Heuristics Over the Atari-2600 Benchmark
            15:00

            Width-based Lookaheads with Learnt Base Policies and Heuristics Over the Atari-2600 Benchmark

            Stefan O'Toole, …

            N2
            N2
            NeurIPS 2021 3 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            TransformerFusion: Monocular RGB Scene Reconstruction using Transformers
            07:14

            TransformerFusion: Monocular RGB Scene Reconstruction using Transformers

            Aljaž Božič, …

            N2
            N2
            NeurIPS 2021 3 years ago

            Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%

            Interested in talks like this? Follow NeurIPS 2021