Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox
Picture for Shiyuan Huang

Shiyuan Huang
Alert button

DiGeo: Discriminative Geometry-Aware Learning for Generalized Few-Shot Object Detection


Mar 16, 2023
Jiawei Ma, Yulei Niu, Jincheng Xu, Shiyuan Huang, Guangxing Han, Shih-Fu Chang

Add code
Alert button

Figure 1 for DiGeo: Discriminative Geometry-Aware Learning for Generalized Few-Shot Object Detection
Figure 2 for DiGeo: Discriminative Geometry-Aware Learning for Generalized Few-Shot Object Detection
Figure 3 for DiGeo: Discriminative Geometry-Aware Learning for Generalized Few-Shot Object Detection
Figure 4 for DiGeo: Discriminative Geometry-Aware Learning for Generalized Few-Shot Object Detection
* CVPR 2023 Camera Ready (Supp Attached). Code Link: https://github.com/Phoenix-V/DiGeo 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

TempCLR: Temporal Alignment Representation with Contrastive Learning


Dec 28, 2022
Yuncong Yang, Jiawei Ma, Shiyuan Huang, Long Chen, Xudong Lin, Guangxing Han, Shih-Fu Chang

Add code
Alert button

Figure 1 for TempCLR: Temporal Alignment Representation with Contrastive Learning
Figure 2 for TempCLR: Temporal Alignment Representation with Contrastive Learning
Figure 3 for TempCLR: Temporal Alignment Representation with Contrastive Learning
Figure 4 for TempCLR: Temporal Alignment Representation with Contrastive Learning

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Video in 10 Bits: Few-Bit VideoQA for Efficiency and Privacy


Oct 18, 2022
Shiyuan Huang, Robinson Piramuthu, Shih-Fu Chang, Gunnar A. Sigurdsson

Add code
Alert button

Figure 1 for Video in 10 Bits: Few-Bit VideoQA for Efficiency and Privacy
Figure 2 for Video in 10 Bits: Few-Bit VideoQA for Efficiency and Privacy
Figure 3 for Video in 10 Bits: Few-Bit VideoQA for Efficiency and Privacy
Figure 4 for Video in 10 Bits: Few-Bit VideoQA for Efficiency and Privacy
* ECCV Workshop 2022 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Towards Fast Adaptation of Pretrained Contrastive Models for Multi-channel Video-Language Retrieval


Jun 05, 2022
Xudong Lin, Simran Tiwari, Shiyuan Huang, Manling Li, Mike Zheng Shou, Heng Ji, Shih-Fu Chang

Add code
Alert button

Figure 1 for Towards Fast Adaptation of Pretrained Contrastive Models for Multi-channel Video-Language Retrieval
Figure 2 for Towards Fast Adaptation of Pretrained Contrastive Models for Multi-channel Video-Language Retrieval
Figure 3 for Towards Fast Adaptation of Pretrained Contrastive Models for Multi-channel Video-Language Retrieval
Figure 4 for Towards Fast Adaptation of Pretrained Contrastive Models for Multi-channel Video-Language Retrieval
* Work in progress 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Multimodal Few-Shot Object Detection with Meta-Learning Based Cross-Modal Prompting


Apr 16, 2022
Guangxing Han, Jiawei Ma, Shiyuan Huang, Long Chen, Rama Chellappa, Shih-Fu Chang

Add code
Alert button

Figure 1 for Multimodal Few-Shot Object Detection with Meta-Learning Based Cross-Modal Prompting
Figure 2 for Multimodal Few-Shot Object Detection with Meta-Learning Based Cross-Modal Prompting
Figure 3 for Multimodal Few-Shot Object Detection with Meta-Learning Based Cross-Modal Prompting
Figure 4 for Multimodal Few-Shot Object Detection with Meta-Learning Based Cross-Modal Prompting
* 22 pages 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Few-Shot Object Detection with Fully Cross-Transformer


Mar 28, 2022
Guangxing Han, Jiawei Ma, Shiyuan Huang, Long Chen, Shih-Fu Chang

Add code
Alert button

Figure 1 for Few-Shot Object Detection with Fully Cross-Transformer
Figure 2 for Few-Shot Object Detection with Fully Cross-Transformer
Figure 3 for Few-Shot Object Detection with Fully Cross-Transformer
Figure 4 for Few-Shot Object Detection with Fully Cross-Transformer
* Accepted by CVPR 2022 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Query Adaptive Few-Shot Object Detection with Heterogeneous Graph Convolutional Networks


Dec 17, 2021
Guangxing Han, Yicheng He, Shiyuan Huang, Jiawei Ma, Shih-Fu Chang

Add code
Alert button

Figure 1 for Query Adaptive Few-Shot Object Detection with Heterogeneous Graph Convolutional Networks
Figure 2 for Query Adaptive Few-Shot Object Detection with Heterogeneous Graph Convolutional Networks
Figure 3 for Query Adaptive Few-Shot Object Detection with Heterogeneous Graph Convolutional Networks
Figure 4 for Query Adaptive Few-Shot Object Detection with Heterogeneous Graph Convolutional Networks
* ICCV 2021 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignment


Apr 15, 2021
Guangxing Han, Shiyuan Huang, Jiawei Ma, Yicheng He, Shih-Fu Chang

Add code
Alert button

Figure 1 for Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignment
Figure 2 for Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignment
Figure 3 for Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignment
Figure 4 for Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignment
* 14 pages 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Task-Adaptive Negative Class Envision for Few-Shot Open-Set Recognition


Dec 24, 2020
Shiyuan Huang, Jiawei Ma, Guangxing Han, Shih-Fu Chang

Add code
Alert button

Figure 1 for Task-Adaptive Negative Class Envision for Few-Shot Open-Set Recognition
Figure 2 for Task-Adaptive Negative Class Envision for Few-Shot Open-Set Recognition
Figure 3 for Task-Adaptive Negative Class Envision for Few-Shot Open-Set Recognition
Figure 4 for Task-Adaptive Negative Class Envision for Few-Shot Open-Set Recognition

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Flow-Distilled IP Two-Stream Networks for Compressed Video Action Recognition


Dec 12, 2019
Shiyuan Huang, Xudong Lin, Svebor Karaman, Shih-Fu Chang

Add code
Alert button

Figure 1 for Flow-Distilled IP Two-Stream Networks for Compressed Video Action Recognition
Figure 2 for Flow-Distilled IP Two-Stream Networks for Compressed Video Action Recognition
Figure 3 for Flow-Distilled IP Two-Stream Networks for Compressed Video Action Recognition
Figure 4 for Flow-Distilled IP Two-Stream Networks for Compressed Video Action Recognition

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
>>