activity
20162024
most citedMiniGPT-v2: large language model as a unified interface for vision-language multi-task learning

67 citations · 101 across the 8 of their papers we have counts for

collaborators

8 papers

cs.CV2024

Learning Video Context as Interleaved Multimodal Sequences

Kevin Qinghong Lin, Pengchuan Zhang, Difei Gao +6

Narrative videos, such as movies, pose significant challenges in video understanding due to their rich contexts (characters, dialogues, storylines) and diverse demands (identify wh…

cs.CL20231 cited

The Role of Chain-of-Thought in Complex Vision-Language Reasoning Task

Yifan Wu, Pengchuan Zhang, Wenhan Xiong +3

The study explores the effectiveness of the Chain-of-Thought approach, known for its proficiency in language tasks by breaking them down into sub-tasks and intermediate steps, in i…

cs.CV202367 cited

MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning

Jun Chen, Deyao Zhu, Xiaoqian Shen +7

Large language models have shown their remarkable capabilities as a general interface for various language-related applications. Motivated by this, we target to build a unified int…

cs.CV2023

Revisiting Kernel Temporal Segmentation as an Adaptive Tokenizer for Long-form Video Understanding

Mohamed Afham, Satya Narayan Shukla, Omid Poursaeed +3

While most modern video understanding models operate on short-range clips, real-world videos are often several minutes long with semantically consistent segments of variable length…

cs.CV2023

EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone

Shraman Pramanick, Yale Song, Sayan Nag +5

Video-language pre-training (VLP) has become increasingly important due to its ability to generalize to various vision and language tasks. However, existing egocentric VLP framewor…

cs.CV20236 cited

UniVTG: Towards Unified Video-Language Temporal Grounding

Kevin Qinghong Lin, Pengchuan Zhang, Joya Chen +5

Video Temporal Grounding (VTG), which aims to ground target clips from videos (such as consecutive intervals or disjoint shots) according to custom language queries (e.g., sentence…