The European Conference on Computer Vision (ECCV) 2022 is being hosted October 23th - 27th. We’re excited to share all the work from SAIL that’s being presented, and you’ll find links to papers, videos and blogs below. Feel free to reach out to the contact authors directly to learn more about the work that’s happening at Stanford!

List of Accepted Papers

Identifying Auxiliary or Adversarial Tasks Using Necessary Condition Analysis for Adversarial Multi-task Video Understanding

Authors: Stephen Su*, Samuel Kwong, Qingyu Zhao, De-An Huang, Juan Carlos Niebles, Ehsan Adeli
Contact: stephensu@cs.stanford.edu
Keywords: video understanding, activity recognition, invariant feature learning, multi-task learning

A Sketch Is Worth a Thousand Words: Image Retrieval with Text and Sketch

Authors: Patsorn Sangkloy, Wittawat Jitkrittum, Diyi Yang, James Hays
Contact: diyiy@stanford.edu
Links: Paper
Keywords: image retrieval; sktech input

AdaAfford: Learning to Adapt Manipulation Affordance for 3D Articulated Objects via Few-shot Interactions

Authors: Yian Wang*, Ruihai Wu*, Kaichun Mo*, Jiaqi Ke, Qingnan Fan, Leonidas J. Guibas, Hao Dong
Contact: kaichun@cs.stanford.edu
Links: Paper | Video | Website
Keywords: 3d shape understanding, robotic vision, affordance learning

GIMO: Gaze-Informed Human Motion Prediction in Context

Authors: Yang Zheng, Yanchao Yang, Kaichun Mo, Jiaman Li, Tao Yu, Yebin Liu, C. Karen Liu, Leonidas J. Guibas
Contact: yzheng18@stanford.edu
Links: Paper | Blog Post | Video | Website
Keywords: human motion prediction, ego-centric vision

Particle Video Revisited: Tracking Through Occlusions Using Point Trajectories

Authors: Adam W. Harley, Zhaoyuan Fang, Katerina Fragkiadaki
Contact: aharley@cs.stanford.edu
Links: Paper | Blog Post | Website
Keywords: computer vision, tracking, optical flow, trajectories, particles

PrivHAR: Recognizing Human Actions From Privacy-preserving Lens

Authors: Carlos Hinojosa, Miguel Marquez, Henry Arguello, Ehsan Adeli, Li Fei-Fei, Juan Carlos Niebles
Contact: carlos.hinojosa@saber.uis.edu.co
Award nominations: Oral Presentation
Links: Paper | Video | Website
Keywords: action and behavior recognition, adversarial learning, computational photography

RankSeg: Adaptive Pixel Classification with Image Category Ranking for Segmentation

Authors: Haodi He, Yuhui Yuan , Xiangyu Yue, Han Hu
Contact: hardyhe@stanford.edu
Links: Paper | Video | Website
Keywords: rank-adaptive, selected-label, image semantic segmentation, image panoptic segmentation, video instance segmentation, video semantic segmentatio

Translating a Visual LEGO Manual to a Machine-Executable Plan

Authors: Ruocheng Wang, Yunzhi Zhang, Jiayuan Mao, Chin-Yi Cheng, Jiajun Wu
Contact: rcwang@stanford.edu
Links: Paper | Website
Keywords: computer vision, compositional 3d modeling, assembly

Unsupervised Segmentation in Real-World Images via Spelke Object Inference

Authors: Honglin Chen, Rahul Venkatesh, Yoni Friedman, Jiajun Wu, Joshua B. Tenenbaum, Daniel L.K. Yamins*, and Daniel M. Bear*
Contact: honglinc@stanford.edu
Award nominations: Oral presentation
Links: Paper | Video | Website
Keywords: unsupervised learning, segmentation, object-centric learning

Video Extrapolation in Space and Time

Authors: Yunzhi Zhang, Jiajun Wu
Contact: yzzhang@cs.stanford.edu
Links: Paper | Website
Keywords: video prediction, novel view synthesis

We look forward to seeing you at ECCV 2022!