activity
20192024
most citedMultimodal Pretraining for Dense Video Captioning

14 citations · 15 across the 3 of their papers we have counts for

collaborators

5 papers

cs.CV2024

Wavelet-Based Image Tokenizer for Vision Transformers

Zhenhai Zhu, Radu Soricut

Non-overlapping patch-wise convolution is the default image tokenizer for all state-of-the-art vision Transformer (ViT) models. Even though many ViT variants have been proposed to…

cs.LG20211 cited

H-Transformer-1D: Fast One-Dimensional Hierarchical Attention for Sequences

Zhenhai Zhu, Radu Soricut

We describe an efficient hierarchical method to compute attention in the Transformer architecture. The proposed attention mechanism exploits a matrix structure similar to the Hiera…

cs.CV202014 cited

Multimodal Pretraining for Dense Video Captioning

Gabriel Huang, Bo Pang, Zhenhai Zhu +2

Learning specific hands-on skills such as cooking, car maintenance, and home repairs increasingly happens via instructional videos. The user experience with such videos is known to…

cs.CL2020

Beyond Instructional Videos: Probing for More Diverse Visual-Textual Grounding on YouTube

Jack Hessel, Zhenhai Zhu, Bo Pang +1

Pretraining from unlabelled web videos has quickly become the de-facto means of achieving high performance on many video understanding tasks. Features are learned via prediction of…

cs.CL2019

A Case Study on Combining ASR and Visual Features for Generating Instructional Video Captions

Jack Hessel, Bo Pang, Zhenhai Zhu +1

Instructional videos get high-traffic on video sharing platforms, and prior work suggests that providing time-stamped, subtask annotations (e.g., "heat the oil in the pan") improve…