Did you miss #ECCV2022 & #DIRA2022? Did you go, but want to relive the experience?

Thanks to the Web Science and Digital Libraries Research Group blog for posting my trip report that covers keynotes, some interesting papers, and my work at #ECCV2022 & the #DIRA2022 workshop.

https://ws-dl.blogspot.com/2022/12/2022-12-23-eccv-2022-and-dira-2022-trip.html

#ComputerVision #InformationRetrieval #ComputerScience #Conference

Ce soir, c'était lecture de papiers d'#ECCV2022 et en particulier ce papier de tracking : "Particle Video Revisited: Tracking Through Occlusions Using Point Trajectories"

Encodeur, corrélation de features, sinusoidal encoding et transformer-like MLP : un joyeux mélange.

https://particle-video-revisited.github.io/

Par Adam W. Harley & team

#AI #ML #Tracking #OpticalFlow #CarnegieMellon

Ce soir, c'était lecture de papiers d'#ECCV2022 et en particulier ce papier de tracking : "Particle Video Revisited: Tracking Through Occlusions Using Point Trajectories"

Encodeur, corrélation features, sinusoidal encoding et transformer-like MLP : un joyeux mélange.

https://particle-video-revisited.github.io/

Par Adam W. Harley & team

#AI #ML #Tracking #OpticalFlow #CarnegieMellon

Ce soir, c'était lecture de papiers d'#ECCV2022 et en particulier ce papier de tracking : "Particle Video Revisited: Tracking Through Occlusions Using Point Trajectories"

Sympa mélange : encodeur, corrélations de feature maps, et transformer-like MLP pour la mise à jour des champs de déplacements

https://particle-video-revisited.github.io/

By Adam W. Harley & team

#AI #ML #Tracking #OpticalFlow #CarnegieMellon

#ECCV2022 #DIRA2022 Many reasons exist for users to conduct image searches: protecting intellectual property, building datasets, providing evidence, or justifying funding. That abstract images are at a disadvantage hurts users leveraging search engines for these use cases.

#ECCV2022 #DIRA2022 Google and Yandex perform better with natural images than with abstract ones achieving a difference in retrievability as high as 54% between images in these categories. These results indicate a clear difference in capability among search engines.

Because Wikipedia is well indexed by search engines, we acquired abstract (diagrams) and natural (photos) images from Wikimedia Commons. We submitted these 380 images to each search engine and recorded how often the search engine returned the same image back. #ECCV2022 #DIRA2022

The major search engines Baidu, Bing, Google, and Yandex support "reverse image search" -- where the user can upload an image and view pages that contain that image or pages that have similar images. #ECCV2022 #DIRA2022

Our preprint of "Abstract Images Have Different Levels of Retrievability Per Reverse Image Search Engine" from #ECCV2022 #DIRA2022 is available. We find Google's and Yandex's reverse image search engines favor finding natural images over abstract ones.

Preprint: https://arxiv.org/abs/2211.02115

RT @AdamWHarley@twitter.com

Very happy to share our #ECCV2022 oral “Particle Video Revisited: Tracking Through Occlusions Using Point Trajectories”

Fine-grained tracking of anything, outperforming optical flow.

project: http://particle-video-revisited.github.io
abs: http://arxiv.org/abs/2204.04153
code: http://github.com/aharley/pips

🐦🔗: https://twitter.com/AdamWHarley/status/1551964737243475968

RT @MohammedAmr1@twitter.com

📢 Our #ECCV2022 paper (and code) on fast accurate depth estimation and reconstruction is out now!

SimpleRecon: 3D Reconstruction without 3D Convolutions
https://nianticlabs.github.io/simplerecon

(1/4)

🐦🔗: https://twitter.com/MohammedAmr1/status/1565459104461721600

😊Such a exhilarating feeling! Checking news from #SIGGRAPH2022, @USENIXSecurity@twitter.com, #eccv2022, #EAUHighlight, @StanfordVR@twitter.com, tools from @crowd_supply@twitter.com, concepts via @andy_matuschak@twitter.com, articles in @QuantaMagazine@twitter.com & more in my feed today, I know I'll keep on learning about CS/IT till🪦!😅

Same principle but instead of OCR, image segmentation.

Source image https://twitter.com/LodeLauwaert/status/1554051803125252097, motivated by https://twitter.com/utopiah/status/1553687507233083399 and thanks to "Highly Accurate Dichotomous Image Segmentation" in a Docker container #ECCV2022

RT @utopiah@twitter.com

With shortcut and browser integration and over a video, to "prove" it was OCR proper : https://twitter.com/utopiah/status/1453021406262874118/photo/1

🐦🔗: https://twitter.com/utopiah/status/1453021406262874118