Yi-Zhe Song

SketchXAI: A First Look at Explainability for Human Sketches

Apr 23, 2023
Zhiyu Qu, Yulia Gryaditskaya, Ke Li, Kaiyue Pang, Tao Xiang, Yi-Zhe Song

Figure 2 for SketchXAI: A First Look at Explainability for Human Sketches

Figure 3 for SketchXAI: A First Look at Explainability for Human Sketches

Figure 4 for SketchXAI: A First Look at Explainability for Human Sketches

* CVPR 2023

Access Paper or Ask Questions

ChiroDiff: Modelling chirographic data with Diffusion Models

Apr 07, 2023
Ayan Das, Yongxin Yang, Timothy Hospedales, Tao Xiang, Yi-Zhe Song

Figure 2 for ChiroDiff: Modelling chirographic data with Diffusion Models

Figure 3 for ChiroDiff: Modelling chirographic data with Diffusion Models

Figure 4 for ChiroDiff: Modelling chirographic data with Diffusion Models

* Accepted at ICLR '23

Access Paper or Ask Questions

Picture that Sketch: Photorealistic Image Generation from Abstract Sketches

Mar 30, 2023
Subhadeep Koley, Ayan Kumar Bhunia, Aneeshan Sain, Pinaki Nath Chowdhury, Tao Xiang, Yi-Zhe Song

Figure 2 for Picture that Sketch: Photorealistic Image Generation from Abstract Sketches

Figure 3 for Picture that Sketch: Photorealistic Image Generation from Abstract Sketches

Figure 4 for Picture that Sketch: Photorealistic Image Generation from Abstract Sketches

* Accepted in CVPR 2023. Project page available at https://subhadeepkoley.github.io/PictureThatSketch

Access Paper or Ask Questions

Sketch2Saliency: Learning to Detect Salient Objects from Human Drawings

Mar 30, 2023
Ayan Kumar Bhunia, Subhadeep Koley, Amandeep Kumar, Aneeshan Sain, Pinaki Nath Chowdhury, Tao Xiang, Yi-Zhe Song

Figure 2 for Sketch2Saliency: Learning to Detect Salient Objects from Human Drawings

Figure 3 for Sketch2Saliency: Learning to Detect Salient Objects from Human Drawings

Figure 4 for Sketch2Saliency: Learning to Detect Salient Objects from Human Drawings

* CVPR 2023. Project page available at https://ayankumarbhunia.github.io/Sketch2Saliency/

Access Paper or Ask Questions

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

Mar 28, 2023
Aneeshan Sain, Ayan Kumar Bhunia, Pinaki Nath Chowdhury, Subhadeep Koley, Tao Xiang, Yi-Zhe Song

Figure 2 for CLIP for All Things Zero-Shot Sketch-Based Image Retrieval, Fine-Grained or Not

Figure 3 for CLIP for All Things Zero-Shot Sketch-Based Image Retrieval, Fine-Grained or Not

Figure 4 for CLIP for All Things Zero-Shot Sketch-Based Image Retrieval, Fine-Grained or Not

* Accepted in CVPR 2023. Project page available at https://aneeshan95.github.io/Sketch_LVM/

Access Paper or Ask Questions

What Can Human Sketches Do for Object Detection?

Mar 27, 2023
Pinaki Nath Chowdhury, Ayan Kumar Bhunia, Aneeshan Sain, Subhadeep Koley, Tao Xiang, Yi-Zhe Song

Figure 2 for What Can Human Sketches Do for Object Detection?

Figure 3 for What Can Human Sketches Do for Object Detection?

Figure 4 for What Can Human Sketches Do for Object Detection?

* Accepted as Top 12 Best Papers. Will be presented in special single-track plenary sessions to all attendees in Computer Vision and Pattern Recognition (CVPR), 2023. Project Page: www.pinakinathc.me/sketch-detect

Access Paper or Ask Questions

DiffTAD: Temporal Action Detection with Proposal Denoising Diffusion

Mar 27, 2023
Sauradip Nag, Xiatian Zhu, Jiankang Deng, Yi-Zhe Song, Tao Xiang

Figure 2 for DiffTAD: Temporal Action Detection with Proposal Denoising Diffusion

Figure 3 for DiffTAD: Temporal Action Detection with Proposal Denoising Diffusion

Figure 4 for DiffTAD: Temporal Action Detection with Proposal Denoising Diffusion

* Technical Report

Access Paper or Ask Questions

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

Mar 25, 2023
Fengyin Lin, Mingkang Li, Da Li, Timothy Hospedales, Yi-Zhe Song, Yonggang Qi

Figure 2 for Zero-Shot Everything Sketch-Based Image Retrieval, and in Explainable Style

Figure 3 for Zero-Shot Everything Sketch-Based Image Retrieval, and in Explainable Style

Figure 4 for Zero-Shot Everything Sketch-Based Image Retrieval, and in Explainable Style

* CVPR 2023 (Highlight)

Access Paper or Ask Questions

Exploiting Unlabelled Photos for Stronger Fine-Grained SBIR

Mar 24, 2023
Aneeshan Sain, Ayan Kumar Bhunia, Subhadeep Koley, Pinaki Nath Chowdhury, Soumitri Chattopadhyay, Tao Xiang, Yi-Zhe Song

Figure 2 for Exploiting Unlabelled Photos for Stronger Fine-Grained SBIR

Figure 3 for Exploiting Unlabelled Photos for Stronger Fine-Grained SBIR

Figure 4 for Exploiting Unlabelled Photos for Stronger Fine-Grained SBIR

* Accepted in CVPR 2023. Project page available at https://aneeshan95.github.io/Sketch_PVT/

Access Paper or Ask Questions