CVPR 2023

We are absolutely thrilled by the exceptional presence of CVSSP this year! Our remarkable team has achieved tremendous success, with a staggering total of 18 papers accepted and the organization of two workshops. What's more, we are honored to announce that our very own Professor Adrian Hilton and Professor John Collomosse will be delivering captivating keynote speeches at two of these workshops.

But that's not all! The renowned Professor Yi-Zhe Song project group(SketchX Lab) has also made a significant impact, with an impressive count of 14 papers accepted. Professor Song himself proudly declares that two of these papers have been recognized as highlighted contributions, showcasing the cutting-edge research we are driving forward. Additionally, we are thrilled to share that one of our papers has been nominated for the prestigious Best Paper award, representing the sole nominee from the entire United Kingdom.

We couldn't be more proud of the exceptional achievements and recognition our teams have garnered this year. These remarkable accomplishments are a testament to the extraordinary talent and unwavering dedication of our researchers, pushing the boundaries of innovation in the computer vision field. 

PAPERS AND POSTERS:

Hu Wang , Yuanhong Chen , Congbo Ma , Jodie Avery , Louise Hull , Gustavo Carneiro

Poster: Multi-Modal Learning With Missing Modality via Shared-Specific Feature Modelling

Jaime Spencer, C. Stella Qian, Michaela Trescakova, Chris Russell, Simon Hadfield, et all.

Paper: The Second Monocular Depth Estimation Challenge

Yu Zeng, Zhe Lin, Jianming Xhang, Qing Liu, John Collomosse, Jason Kuen, Vishal M. Patel

Paper: SceneComposer: Any-Level Semantic Image Synthesis

* CVPR Highlight

Subhadeep Koley, Ayan Kumar Bhunia, Aneeshan Sain, Pinaki Nath Chowdhury, Tao Xiang, Yi-Zhe Song

Paper: Picture that Sketch: Photorealistic Image Generation from Abstract Sketches Picture that Sketch: Photorealistic Image Generation from Abstract Sketches

Ke Li, Kaiyue Pang, Yi-Zhe Song

Paper: Photo Pre-Training, But for Sketch

Zhiyu Qu, Yulia Gryaditskaya, Ke Li, Kaiyue Pang, Tao Xiang, Yi-Zhe Song

Paper: SketchXAI: A First Look at Explainability for Human Sketches

Ayan Kumar Bhunia, Subhadeep Koley, Amandeep Kumar, Aneeshan Sain, Pinaki Nath Chowdhury, Tao Xiang, Yi-Zhe Song

Paper: Sketch2Saliency: Learning to Detect Salient Objects from Human Drawings Sketch2Saliency: Learning to Detect Salient Objects from Human Drawings

Pinaki Nath Chowdhury, Ayan Kumar Bhunia, Aneeshan Sain, Subhadeep Koley, Tao Xiang, Yi-Zhe Song,

Paper: What Can Human Sketches Do for Object Detection?

* BEST PAPER AWARD CANDIDATE

Fengyin Lin, Mingkang Li, Yonggang Qi, Da Li, Timothy Hospedales, Yi-Zhe Song

Paper: Zero-Shot Everything Sketch-Based Image Retrieval, and in Explainable Style 

* CVPR Highlight

Pinaki Nath Chowdhury, Ayan Kumar Bhunia, Aneeshan Sain, Subhadeep Koley, Tao Xiang, Yi-Zhe Song

Paper: SceneTrilogy: On Human Scene-Sketch and its Complementarity with Photo and Text SceneTrilogy: On Human Scene-Sketch and its Complementarity with Photo and Text

Aneeshan Sain, Ayan Kumar Bhunia, Subhadeep Koley, Pinaki Nath Chowdhury, Soumitri Chattopadhyay, Tao Xiang, Yi-Zhe Song 

Paper: Exploiting Unlabelled Photos for Stronger Fine-Grained SBIR Exploiting Unlabelled Photos for Stronger Fine-Grained SBIR

Aneeshan Sain, Ayan Kumar Bhunia, Pinaki Nath Chowdhury, Subhadeep Koley, Tao Xiang, Yi-Zhe Song

Paper: CLIP for All Things Zero-Shot Sketch-Based Image Retrieval, Fine-Grained or Not CLIP for All Things Zero-Shot Sketch-Based Image Retrieval, Fine-Grained or Not

Abhra Chaudhuri, Ayan Kumar Bhunia, Yi-Zhe Song, Anjan Dutta

Paper: Data-Free Sketch-Based Image Retrieval Data-Free Sketch-Based Image Retrieval

Dongliang Chang, Yujun Tong, Ruoyi Du, Timothy Hospedales, Yi-Zhe Song, Zhanyu Ma

Paper:  An Erudite Fine-Grained Visual Classification Model

Ruoyi Du, Dongliang Chang, Kongming Liang, Timothy Hospedales, Yi-Zhe Song, Zhanyu Ma

Paper: On-the-fly Category Discovery

Xiao Han, Xiatian Zhu, Licheng Yu, Li Zhang, Yi-Zhe Song, Tao Xiang

Paper:  FAME-ViL: Multi-Tasking Vision-Language Model for Heterogeneous Fashion Tasks 

* CVPR Highlight

Sauradip Nag, Xiatian Zhu, Yi-Zhe Song, Tao Xiang

Paper: Post-Processing Temporal Action Detection

Kar Balan , Shruti Agarwal , Simon Jenni , Andy Parsons , Andrew Gilbert , John Collomosse

Poster: EKILA: Synthetic Media Provenance and Attribution for Generative Art

WORKSHOPS:

Dr Armin Mustafa - Organiser

The 3rd International Workshop on Dynamics Scene Reconstruction

Dr Jaime Spencer-Martin - Organiser

Prof Richard Bowden: Co-organiser

Dr Simon Hadfield: Co-organiser

The Second Monocular Depth Estimation Challenge

KEYNOTES:

Prof Adria Hilton

Co-chair of 2 workshops: Computer Vision for Sports, Dynamic Scene Reconstruction

Keynote speaker: OmniVision Workshop

Prof John Collomosse

Keynote speaker: Video Copy Detection Workshop