Large-scale Pretraining for Visual Dialog:A Simple State-of-the-Art Baseline

July 15, 2020

Abstract

Prior work in visual dialog has focused on training deep neural models on VisDial [1] in isolation. Instead, we present an approach to leverage pretraining on related vision-language datasets before transferring to visual dialog. We adapt the recently proposed ViLBERT model [2] for multi-turn visually-grounded conversations. Our model is pretrained on the Conceptual Captions [3] and Visual Question Answering [4] datasets, and finetuned on VisDial. Our best single model outperforms prior published work by >1% absolute on NDCG and MRR. Next, we find that additional finetuning using “dense” annotations in VisDial leads to even higher NDCG – more than 10% over our base model – but hurts MRR – more than 17% below our base model! This highlights a trade-off between the two primary metrics – NDCG and MRR – which we find is due to dense annotations not correlating well with the original ground-truth answers to questions.

Download the Paper

AUTHORS

Written by

Devi Parikh

Abhishek Das

Dhruv Batra

Vishvak Murahari

Publisher

ECCV

Research Topics

Natural Language Processing (NLP)

Computer Vision

Related Publications

February 11, 2026

RESEARCH

COMPUTER VISION

UniT: Unified Multimodal Chain-of-Thought Test-time Scaling

Leon Liangyu Chen, Haoyu Ma, Zhipeng Fan, Ziqi Huang, Animesh Sinha, Xiaoliang Dai, Jialiang Wang, Zecheng He, Jianwei Yang, Chunyuan Li, Junzhe Sun, Chu Wang, Serena Yeung-Levy, Felix Juefei-Xu

February 11, 2026

Read the Paper

February 10, 2026

NLP

AIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agents

Alisia Lupidi, Bhavul Gauri, Thomas Simon Foster, Bassel Al Omari, Despoina Magka, Alberto Pepe, Alexis Audran-Reiss, Muna Aghamelu, Nicolas Baldwin, Lucia Cipolina-Kun, Jean-Christophe Gagnon-Audet, Chee Hau Leow, Sandra Lefdal, Hossam Mossalam, Abhinav Moudgil, Saba Nazir, Emanuel Tewolde, Isabel Urrego, Jordi Armengol Estape, Amar Budhiraja, Gaurav Chaurasia, Abhishek Charnalia, Derek Dunfield, Karen Hambardzumyan, Daniel Izcovich, Martin Josifoski, Ishita Mediratta, Kelvin Niu, Parth Pathak, Michael Shvartsman, Edan Toledo, Anton Protopopov, Roberta Raileanu, Alexander Miller, Tatiana Shavrina, Jakob Foerster, Yoram Bachrach

February 10, 2026

Read the Paper

January 02, 2026

COMPUTER VISION

PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation

Yuanhao Cai, Kunpeng Li, Menglin Jia, Jialiang Wang, Junzhe Sun, Feng Liang, Weifeng Chen, Felix Xu, Chu Wang, Ali Thabet, Xiaoliang Dai, Xuan Ju, Alan Yuille, Ji Hou