activity
20182026
most citedLearning Object Detection from Captions via Textual Scene Attributes

6 citations · 8 across the 18 of their papers we have counts for

collaborators
Showing 2023Show all

6 papers · 1 filter

cs.CV20231 cited

Unsupervised Universal Image Segmentation

Dantong Niu, Xudong Wang, Xinyang Han +3

Several unsupervised image segmentation approaches have been proposed which eliminate the need for dense manually-annotated segmentation masks; current models separately handle eit…

cs.CV2023

Recursive Visual Programming

Jiaxin Ge, Sanjay Subramanian, Baifeng Shi +2

Visual Programming (VP) has emerged as a powerful framework for Visual Question Answering (VQA). By generating and executing bespoke code for each question, these methods demonstra…

cs.CV2023

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

Dantong Niu, Amir Bar, Roei Herzig +2

Existing video-based action recognition systems typically require dense annotation and struggle in environments when there is significant distribution shift relative to the trainin…

cs.CV2023

Compositional Chain-of-Thought Prompting for Large Multimodal Models

Chancharik Mitra, Brandon Huang, Trevor Darrell +1

The combination of strong visual backbones and Large Language Model (LLM) reasoning has led to Large Multimodal Models (LMMs) becoming the current standard for a wide range of visi…

cs.CV202312 cited

Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models

Sivan Doveh, Assaf Arbelle, Sivan Harary +9

Vision and Language (VL) models offer an effective method for aligning representation spaces of images and text, leading to numerous applications such as cross-modal retrieval, vis…

cs.CV2023

Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs

Roei Herzig, Alon Mendelson, Leonid Karlinsky +4

Vision and language models (VLMs) have demonstrated remarkable zero-shot (ZS) performance in a variety of tasks. However, recent works have shown that even the best VLMs struggle t…