Alert button

"Text": models, code, and papers
Alert button

Multimodal Adaptation of CLIP for Few-Shot Action Recognition

Aug 03, 2023
Jiazheng Xing, Mengmeng Wang, Xiaojun Hou, Guang Dai, Jingdong Wang, Yong Liu

Figure 1 for Multimodal Adaptation of CLIP for Few-Shot Action Recognition
Figure 2 for Multimodal Adaptation of CLIP for Few-Shot Action Recognition
Figure 3 for Multimodal Adaptation of CLIP for Few-Shot Action Recognition
Figure 4 for Multimodal Adaptation of CLIP for Few-Shot Action Recognition
Viaarxiv icon

Lost In Translation: Generating Adversarial Examples Robust to Round-Trip Translation

Jul 24, 2023
Neel Bhandari, Pin-Yu Chen

Figure 1 for Lost In Translation: Generating Adversarial Examples Robust to Round-Trip Translation
Figure 2 for Lost In Translation: Generating Adversarial Examples Robust to Round-Trip Translation
Figure 3 for Lost In Translation: Generating Adversarial Examples Robust to Round-Trip Translation
Figure 4 for Lost In Translation: Generating Adversarial Examples Robust to Round-Trip Translation
Viaarxiv icon

CLIP-Count: Towards Text-Guided Zero-Shot Object Counting

May 12, 2023
Ruixiang Jiang, Lingbo Liu, Changwen Chen

Figure 1 for CLIP-Count: Towards Text-Guided Zero-Shot Object Counting
Figure 2 for CLIP-Count: Towards Text-Guided Zero-Shot Object Counting
Figure 3 for CLIP-Count: Towards Text-Guided Zero-Shot Object Counting
Figure 4 for CLIP-Count: Towards Text-Guided Zero-Shot Object Counting
Viaarxiv icon

Augmenting CLIP with Improved Visio-Linguistic Reasoning

Jul 27, 2023
Samyadeep Basu, Maziar Sanjabi, Daniela Massiceti, Shell Xu Hu, Soheil Feizi

Figure 1 for Augmenting CLIP with Improved Visio-Linguistic Reasoning
Figure 2 for Augmenting CLIP with Improved Visio-Linguistic Reasoning
Figure 3 for Augmenting CLIP with Improved Visio-Linguistic Reasoning
Figure 4 for Augmenting CLIP with Improved Visio-Linguistic Reasoning
Viaarxiv icon

AdversarialWord Dilution as Text Data Augmentation in Low-Resource Regime

May 16, 2023
Junfan Chen, Richong Zhang, Zheyan Luo, Chunming Hu, Yongyi Mao

Figure 1 for AdversarialWord Dilution as Text Data Augmentation in Low-Resource Regime
Figure 2 for AdversarialWord Dilution as Text Data Augmentation in Low-Resource Regime
Figure 3 for AdversarialWord Dilution as Text Data Augmentation in Low-Resource Regime
Figure 4 for AdversarialWord Dilution as Text Data Augmentation in Low-Resource Regime
Viaarxiv icon

Cross Encoding as Augmentation: Towards Effective Educational Text Classification

May 31, 2023
Hyun Seung Lee, Seungtaek Choi, Yunsung Lee, Hyeongdon Moon, Shinhyeok Oh, Myeongho Jeong, Hyojun Go, Christian Wallraven

Figure 1 for Cross Encoding as Augmentation: Towards Effective Educational Text Classification
Figure 2 for Cross Encoding as Augmentation: Towards Effective Educational Text Classification
Figure 3 for Cross Encoding as Augmentation: Towards Effective Educational Text Classification
Figure 4 for Cross Encoding as Augmentation: Towards Effective Educational Text Classification
Viaarxiv icon

Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment

May 19, 2023
Tianshu Yu, Haoyu Gao, Ting-En Lin, Min Yang, Yuchuan Wu, Wentao Ma, Chao Wang, Fei Huang, Yongbin Li

Figure 1 for Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment
Figure 2 for Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment
Figure 3 for Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment
Figure 4 for Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment
Viaarxiv icon

Deconstructing Classifiers: Towards A Data Reconstruction Attack Against Text Classification Models

Jun 23, 2023
Adel Elmahdy, Ahmed Salem

Figure 1 for Deconstructing Classifiers: Towards A Data Reconstruction Attack Against Text Classification Models
Figure 2 for Deconstructing Classifiers: Towards A Data Reconstruction Attack Against Text Classification Models
Figure 3 for Deconstructing Classifiers: Towards A Data Reconstruction Attack Against Text Classification Models
Figure 4 for Deconstructing Classifiers: Towards A Data Reconstruction Attack Against Text Classification Models
Viaarxiv icon

Text-To-Concept (and Back) via Cross-Model Alignment

May 10, 2023
Mazda Moayeri, Keivan Rezaei, Maziar Sanjabi, Soheil Feizi

Figure 1 for Text-To-Concept (and Back) via Cross-Model Alignment
Figure 2 for Text-To-Concept (and Back) via Cross-Model Alignment
Figure 3 for Text-To-Concept (and Back) via Cross-Model Alignment
Figure 4 for Text-To-Concept (and Back) via Cross-Model Alignment
Viaarxiv icon

StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data

Aug 20, 2023
Yanda Li, Chi Zhang, Gang Yu, Zhibin Wang, Bin Fu, Guosheng Lin, Chunhua Shen, Ling Chen, Yunchao Wei

Figure 1 for StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data
Figure 2 for StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data
Figure 3 for StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data
Figure 4 for StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data
Viaarxiv icon