activity
20152023
most citedReferring Transformer: A One-step Approach to Multi-task Visual Grounding

73 citations · 309 across the 34 of their papers we have counts for

collaborators
Showing 2019Show all

9 papers · 1 filter

cs.CV2019

Improved Few-Shot Visual Classification

Peyman Bateni, Raghav Goyal, Vaden Masrani +2

Few-shot learning is a fundamental task in computer vision that carries the promise of alleviating the need for exhaustively labeled data. Most few-shot learning approaches to date…

cs.CV2019

Generating Videos of Zero-Shot Compositions of Actions and Objects

Megha Nawhal, Mengyao Zhai, Andreas Lehrmann +2

Human activity videos involve rich, varied interactions between people and objects. In this paper we develop methods for generating such videos -- making progress toward addressing…

cs.CV2019

OptiBox: Breaking the Limits of Proposals for Visual Grounding

Zicong Fan, Si Yi Meng, Leonid Sigal +1

The problem of language grounding has attracted much attention in recent years due to its pivotal role in more general image-lingual high level reasoning tasks (e.g., image caption…

cs.CV2019★ 1 cited

Watch, Listen and Tell: Multi-modal Weakly Supervised Dense Event Captioning

Tanzila Rahman, Bicheng Xu, Leonid Sigal

Multi-modal learning, particularly among imaging and linguistic modalities, has made amazing strides in many high-level fundamental visual understanding problems, ranging from lang…

cs.CV2019★ 9 cited

DwNet: Dense warp-based network for pose-guided human video generation

Polina Zablotskaia, Aliaksandr Siarohin, Bo Zhao +1

Generation of realistic high-resolution videos of human subjects is a challenging and important task in computer vision. In this paper, we focus on human motion transfer - generati…

cs.CV2019

LayoutVAE: Stochastic Scene Layout Generation From a Label Set

Akash Abdu Jyothi, Thibaut Durand, Jiawei He +2

Recently there is an increasing interest in scene generation within the research community. However, models used for generating scene layouts from textual description largely ignor…