Too Large; Data Reduction for Vision-Language Pre-Training

2 code implementations • ICCV 2023 • Alex Jinpeng Wang, Kevin Qinghong Lin, David Junhao Zhang, Stan Weixian Lei, Mike Zheng Shou

Specifically, TL;DR can compress the mainstream VLP datasets at a high ratio, e. g., reduce well-cleaned CC3M dataset from 2. 82M to 0. 67M ($\sim$24\%) and noisy YFCC15M from 15M to 2. 5M ($\sim$16. 7\%).

Symbolic Replay: Scene Graph as Prompt for Continual Learning on VQA Task

1 code implementation • 24 Aug 2022 • Stan Weixian Lei, Difei Gao, Jay Zhangjie Wu, Yuxuan Wang, Wei Liu, Mengmi Zhang, Mike Zheng Shou

However, CL on VQA involves not only the expansion of label sets (new Answer sets).

Continual Learning Question Answering +1

GEB+: A Benchmark for Generic Event Boundary Captioning, Grounding and Retrieval

1 code implementation • 1 Apr 2022 • Yuxuan Wang, Difei Gao, Licheng Yu, Stan Weixian Lei, Matt Feiszli, Mike Zheng Shou

In this paper, we introduce a new dataset called Kinetic-GEB+.

Boundary Captioning Boundary Grounding +2

AssistQ: Affordance-centric Question-driven Task Completion for Egocentric Assistant

4 code implementations • 8 Mar 2022 • Benita Wong, Joya Chen, You Wu, Stan Weixian Lei, Dongxing Mao, Difei Gao, Mike Zheng Shou

In this paper, we define a new task called Affordance-centric Question-driven Task Completion, where the AI assistant should learn from instructional videos to provide step-by-step help in the user's view.

Visual Question Answering (VQA)

AssistSR: Task-oriented Video Segment Retrieval for Personal AI Assistant

2 code implementations • 30 Nov 2021 • Stan Weixian Lei, Difei Gao, Yuxuan Wang, Dongxing Mao, Zihan Liang, Lingmin Ran, Mike Zheng Shou

In contrast, we present a new task called Task-oriented Question-driven Video Segment Retrieval (TQVSR).

Question Answering Retrieval +2

Generic Event Boundary Detection: A Benchmark for Event Segmentation

2 code implementations • ICCV 2021 • Mike Zheng Shou, Stan Weixian Lei, Weiyao Wang, Deepti Ghadiyaram, Matt Feiszli

This paper presents a novel task together with a new benchmark for detecting generic, taxonomy-free event boundaries that segment a whole video into chunks.

Action Detection Boundary Detection +3