Alert button
Picture for Anna Rohrbach

Anna Rohrbach

Alert button

Object-based (yet Class-agnostic) Video Domain Adaptation

Nov 29, 2023
Dantong Niu, Amir Bar, Roei Herzig, Trevor Darrell, Anna Rohrbach

Viaarxiv icon

MammalNet: A Large-scale Video Benchmark for Mammal Recognition and Behavior Understanding

Jun 01, 2023
Jun Chen, Ming Hu, Darren J. Coker, Michael L. Berumen, Blair Costelloe, Sara Beery, Anna Rohrbach, Mohamed Elhoseiny

Figure 1 for MammalNet: A Large-scale Video Benchmark for Mammal Recognition and Behavior Understanding
Figure 2 for MammalNet: A Large-scale Video Benchmark for Mammal Recognition and Behavior Understanding
Figure 3 for MammalNet: A Large-scale Video Benchmark for Mammal Recognition and Behavior Understanding
Figure 4 for MammalNet: A Large-scale Video Benchmark for Mammal Recognition and Behavior Understanding
Viaarxiv icon

Simple Token-Level Confidence Improves Caption Correctness

May 11, 2023
Suzanne Petryk, Spencer Whitehead, Joseph E. Gonzalez, Trevor Darrell, Anna Rohrbach, Marcus Rohrbach

Figure 1 for Simple Token-Level Confidence Improves Caption Correctness
Figure 2 for Simple Token-Level Confidence Improves Caption Correctness
Figure 3 for Simple Token-Level Confidence Improves Caption Correctness
Figure 4 for Simple Token-Level Confidence Improves Caption Correctness
Viaarxiv icon

Focus! Relevant and Sufficient Context Selection for News Image Captioning

Dec 01, 2022
Mingyang Zhou, Grace Luo, Anna Rohrbach, Zhou Yu

Figure 1 for Focus! Relevant and Sufficient Context Selection for News Image Captioning
Figure 2 for Focus! Relevant and Sufficient Context Selection for News Image Captioning
Figure 3 for Focus! Relevant and Sufficient Context Selection for News Image Captioning
Figure 4 for Focus! Relevant and Sufficient Context Selection for News Image Captioning
Viaarxiv icon

Shape-Guided Diffusion with Inside-Outside Attention

Dec 01, 2022
Dong Huk Park, Grace Luo, Clayton Toste, Samaneh Azadi, Xihui Liu, Maka Karalashvili, Anna Rohrbach, Trevor Darrell

Figure 1 for Shape-Guided Diffusion with Inside-Outside Attention
Figure 2 for Shape-Guided Diffusion with Inside-Outside Attention
Figure 3 for Shape-Guided Diffusion with Inside-Outside Attention
Figure 4 for Shape-Guided Diffusion with Inside-Outside Attention
Viaarxiv icon

G^3: Geolocation via Guidebook Grounding

Nov 28, 2022
Grace Luo, Giscard Biamby, Trevor Darrell, Daniel Fried, Anna Rohrbach

Figure 1 for G^3: Geolocation via Guidebook Grounding
Figure 2 for G^3: Geolocation via Guidebook Grounding
Figure 3 for G^3: Geolocation via Guidebook Grounding
Figure 4 for G^3: Geolocation via Guidebook Grounding
Viaarxiv icon

TL;DW? Summarizing Instructional Videos with Task Relevance & Cross-Modal Saliency

Aug 14, 2022
Medhini Narasimhan, Arsha Nagrani, Chen Sun, Michael Rubinstein, Trevor Darrell, Anna Rohrbach, Cordelia Schmid

Figure 1 for TL;DW? Summarizing Instructional Videos with Task Relevance & Cross-Modal Saliency
Figure 2 for TL;DW? Summarizing Instructional Videos with Task Relevance & Cross-Modal Saliency
Figure 3 for TL;DW? Summarizing Instructional Videos with Task Relevance & Cross-Modal Saliency
Figure 4 for TL;DW? Summarizing Instructional Videos with Task Relevance & Cross-Modal Saliency
Viaarxiv icon

Structured Video Tokens @ Ego4D PNR Temporal Localization Challenge 2022

Jun 15, 2022
Elad Ben-Avraham, Roei Herzig, Karttikeya Mangalam, Amir Bar, Anna Rohrbach, Leonid Karlinsky, Trevor Darrell, Amir Globerson

Figure 1 for Structured Video Tokens @ Ego4D PNR Temporal Localization Challenge 2022
Figure 2 for Structured Video Tokens @ Ego4D PNR Temporal Localization Challenge 2022
Figure 3 for Structured Video Tokens @ Ego4D PNR Temporal Localization Challenge 2022
Viaarxiv icon

Bringing Image Scene Structure to Video via Frame-Clip Consistency of Object Tokens

Jun 15, 2022
Elad Ben-Avraham, Roei Herzig, Karttikeya Mangalam, Amir Bar, Anna Rohrbach, Leonid Karlinsky, Trevor Darrell, Amir Globerson

Figure 1 for Bringing Image Scene Structure to Video via Frame-Clip Consistency of Object Tokens
Figure 2 for Bringing Image Scene Structure to Video via Frame-Clip Consistency of Object Tokens
Figure 3 for Bringing Image Scene Structure to Video via Frame-Clip Consistency of Object Tokens
Figure 4 for Bringing Image Scene Structure to Video via Frame-Clip Consistency of Object Tokens
Viaarxiv icon

Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectly

Apr 28, 2022
Spencer Whitehead, Suzanne Petryk, Vedaad Shakib, Joseph Gonzalez, Trevor Darrell, Anna Rohrbach, Marcus Rohrbach

Figure 1 for Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectly
Figure 2 for Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectly
Figure 3 for Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectly
Figure 4 for Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectly
Viaarxiv icon