31 MBZUAI papers accepted at CVPR

Friday, June 17, 2022

At the 34th annual Conference on Computer Vision and Pattern Recognition (CVPR 2022) to take place in New Orleans, Louisiana, MBZUAI faculty and students will present 31 papers, including 6 oral presentations. For the conference a total of 2,063 papers will be published out of 8,161 submissions, with 342 of them selected for oral presentation.

In total, 7 MBZUAI faculty appear on more than one paper. Topping the list, Professors Fahad Khan and Shijian Lu have 9 and 8 papers respectively with their co-authors. MBZUAI researchers collaborated with 57 institutions that span the public and private sector. In total when publishing their work, MBZUAI faculty connect the university to 16 countries across 5 continents with China, the U.S., Australia and Korea as the top four countries.

Research highlights

The cost of acquiring labeled data is significantly higher for video than for images. Several members of faculty have papers on the challenges of using unlabeled (video) data for solving exciting computer vision problems. Professors Salman Khan, Fahad Khan, and Muhammad Haris Khan (not related), and their co-authors, published “Self-Supervised Video Transformer”, “Generative Cooperative Learning for Unsupervised Video Anomaly Detection” and “Spatio-temporal Relation Modeling for Few-shot Action Recognition.” 

The papers propose novel methods for autonomously and accurately analyzing video content by learning useful representations without extensive manual annotations and test their methods against established benchmarks. Interestingly, all three papers have implications for video understanding, comprehending the magnitude of videos uploaded via social media channels, and even personal digital assistant that sorts through your library and turns your boring videos into shareable moments.

Of course with 31 published papers, it’s impossible to properly acknowledge all of the dedication that has gone into this year’s slate of accepted papers. We congratulate our faculty and students, who are presenting papers at CVPR 2022, including Professor Eric Xing, Associate Professors of Computer Vision Fahad KhanHao Li, Salman Khan, and Kun Zhang; Assistant Professors of Computer Vision Rao Muhammad AnwerHisham Cholakkal, Hang Dai, Muhammad Haris Khan, Pengtao Xie, Assistant Professor of Machine Learning Huan Xiong; Adjunct Associate Professor of Computer Vision Shijian Lu, and Affiliated Assistant Professor of Computer Vision Min Xu.

To follow our scientists and stay up-to-date with the latest research from MBZUAI follow us on LinkedInTwitter, and Instagram.

CVPR is organized by the Computer Vision Foundation (CVF) and the Institute of Electrical and Electronics Engineers (IEEE). Conference proceedings will be publicly available via the CVF website, with final versions posted to IEEE Xplore after the conference.

Related

thumbnail
Wednesday, December 18, 2024

AI and the Arabic language: Preserving cultural heritage and enabling future discovery

The Arabic language is underrepresented in the digital world, making AI inaccessible for many of its 400.....

  1. atlas ,
  2. language ,
  3. Arabic LLM ,
  4. United Nations ,
  5. Arabic language ,
  6. jais ,
  7. llms ,
  8. large language models ,
Read More
thumbnail
Thursday, December 12, 2024

Solving complex problems with LLMs: A new prompting strategy presented at NeurIPS

Martin Takáč and Zangir Iklassov's 'self-guided exploration' significantly improves LLM performance in solving combinatorial problems.

  1. processing ,
  2. prompting ,
  3. problem-solving ,
  4. llms ,
  5. neurips ,
  6. machine learning ,
Read More