Picture for Jinxiang Liu

Jinxiang Liu

DENOISER: Rethinking the Robustness for Open-Vocabulary Action Recognition

Add code
Apr 23, 2024
Figure 1 for DENOISER: Rethinking the Robustness for Open-Vocabulary Action Recognition
Figure 2 for DENOISER: Rethinking the Robustness for Open-Vocabulary Action Recognition
Figure 3 for DENOISER: Rethinking the Robustness for Open-Vocabulary Action Recognition
Figure 4 for DENOISER: Rethinking the Robustness for Open-Vocabulary Action Recognition
Viaarxiv icon

Audio-Visual Segmentation via Unlabeled Frame Exploitation

Add code
Mar 17, 2024
Figure 1 for Audio-Visual Segmentation via Unlabeled Frame Exploitation
Figure 2 for Audio-Visual Segmentation via Unlabeled Frame Exploitation
Figure 3 for Audio-Visual Segmentation via Unlabeled Frame Exploitation
Figure 4 for Audio-Visual Segmentation via Unlabeled Frame Exploitation
Viaarxiv icon

Audio-aware Query-enhanced Transformer for Audio-Visual Segmentation

Add code
Jul 25, 2023
Figure 1 for Audio-aware Query-enhanced Transformer for Audio-Visual Segmentation
Figure 2 for Audio-aware Query-enhanced Transformer for Audio-Visual Segmentation
Figure 3 for Audio-aware Query-enhanced Transformer for Audio-Visual Segmentation
Figure 4 for Audio-aware Query-enhanced Transformer for Audio-Visual Segmentation
Viaarxiv icon

Annotation-free Audio-Visual Segmentation

Add code
May 19, 2023
Figure 1 for Annotation-free Audio-Visual Segmentation
Figure 2 for Annotation-free Audio-Visual Segmentation
Figure 3 for Annotation-free Audio-Visual Segmentation
Figure 4 for Annotation-free Audio-Visual Segmentation
Viaarxiv icon

DiffusionSeg: Adapting Diffusion Towards Unsupervised Object Discovery

Add code
Mar 17, 2023
Figure 1 for DiffusionSeg: Adapting Diffusion Towards Unsupervised Object Discovery
Figure 2 for DiffusionSeg: Adapting Diffusion Towards Unsupervised Object Discovery
Figure 3 for DiffusionSeg: Adapting Diffusion Towards Unsupervised Object Discovery
Figure 4 for DiffusionSeg: Adapting Diffusion Towards Unsupervised Object Discovery
Viaarxiv icon

Constraint and Union for Partially-Supervised Temporal Sentence Grounding

Add code
Feb 20, 2023
Figure 1 for Constraint and Union for Partially-Supervised Temporal Sentence Grounding
Figure 2 for Constraint and Union for Partially-Supervised Temporal Sentence Grounding
Figure 3 for Constraint and Union for Partially-Supervised Temporal Sentence Grounding
Figure 4 for Constraint and Union for Partially-Supervised Temporal Sentence Grounding
Viaarxiv icon

Distilling Vision-Language Pre-training to Collaborate with Weakly-Supervised Temporal Action Localization

Add code
Dec 19, 2022
Figure 1 for Distilling Vision-Language Pre-training to Collaborate with Weakly-Supervised Temporal Action Localization
Figure 2 for Distilling Vision-Language Pre-training to Collaborate with Weakly-Supervised Temporal Action Localization
Figure 3 for Distilling Vision-Language Pre-training to Collaborate with Weakly-Supervised Temporal Action Localization
Figure 4 for Distilling Vision-Language Pre-training to Collaborate with Weakly-Supervised Temporal Action Localization
Viaarxiv icon

Exploiting Transformation Invariance and Equivariance for Self-supervised Sound Localisation

Add code
Jun 26, 2022
Figure 1 for Exploiting Transformation Invariance and Equivariance for Self-supervised Sound Localisation
Figure 2 for Exploiting Transformation Invariance and Equivariance for Self-supervised Sound Localisation
Figure 3 for Exploiting Transformation Invariance and Equivariance for Self-supervised Sound Localisation
Figure 4 for Exploiting Transformation Invariance and Equivariance for Self-supervised Sound Localisation
Viaarxiv icon

A 3D Mesh-based Lifting-and-Projection Network for Human Pose Transfer

Add code
Sep 24, 2021
Figure 1 for A 3D Mesh-based Lifting-and-Projection Network for Human Pose Transfer
Figure 2 for A 3D Mesh-based Lifting-and-Projection Network for Human Pose Transfer
Figure 3 for A 3D Mesh-based Lifting-and-Projection Network for Human Pose Transfer
Figure 4 for A 3D Mesh-based Lifting-and-Projection Network for Human Pose Transfer
Viaarxiv icon