371 citations · 3.9k across the 110 of their papers we have counts for
22 papers · 1 filter
MLP Architectures for Vision-and-Language Modeling: An Empirical Study
Yixin Nie, Linjie Li, Zhe Gan +6
We initiate the first empirical study on the use of MLP architectures for vision-and-language (VL) fusion. Through extensive experiments on 5 VL tasks and 5 robust VQA benchmarks,…
Injecting Semantic Concepts into End-to-End Image Captioning
Zhiyuan Fang, Jianfeng Wang, Xiaowei Hu +5
Tremendous progress has been made in recent years in developing better image captioning models, yet most of them rely on a separate object detector to extract regional features. Re…
UFO: A UniFied TransfOrmer for Vision-Language Representation Learning
Jianfeng Wang, Xiaowei Hu, Zhe Gan +5
In this paper, we propose a single UniFied transfOrmer (UFO), which is capable of processing either unimodal inputs (e.g., image or language) or multimodal inputs (e.g., the concat…
SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning
Kevin Lin, Linjie Li, Chung-Ching Lin +5
The canonical approach to video captioning dictates a caption generation model to learn from offline-extracted dense video features. These feature extractors usually operate on vid…
VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modeling
Tsu-Jui Fu, Linjie Li, Zhe Gan +4
A great challenge in video-language (VidL) modeling lies in the disconnection between fixed video representations extracted from image/video understanding models and downstream Vid…
Scaling Up Vision-Language Pre-training for Image Captioning
Xiaowei Hu, Zhe Gan, Jianfeng Wang +4
In recent years, we have witnessed significant performance boost in the image captioning task based on vision-language pre-training (VLP). Scale is believed to be an important fact…
UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modeling
Zhengyuan Yang, Zhe Gan, Jianfeng Wang +5
We propose UniTAB that Unifies Text And Box outputs for grounded vision-language (VL) modeling. Grounded VL tasks such as grounded captioning require the model to generate a text d…
Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models
Boxin Wang, Chejian Xu, Shuohang Wang +5
Large-scale pre-trained language models have achieved tremendous success across a wide range of natural language understanding (NLU) tasks, even surpassing human performance. Howev…
An Empirical Study of Training End-to-End Vision-and-Language Transformers
Zi-Yi Dou, Yichong Xu, Zhe Gan +9
Vision-and-language (VL) pre-training has proven to be highly effective on various VL downstream tasks. While recent work has shown that fully transformer-based VL models can be mo…
An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA
Zhengyuan Yang, Zhe Gan, Jianfeng Wang +4
Knowledge-based visual question answering (VQA) involves answering questions that require external knowledge not present in the image. Existing methods first retrieve knowledge fro…
Simpler, Faster, Stronger: Breaking The log-K Curse On Contrastive Learners With FlatNCE
Junya Chen, Zhe Gan, Xuan Li +10
InfoNCE-based contrastive representation learners, such as SimCLR, have been tremendously successful in recent years. However, these contrastive schemes are notoriously resource de…
VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation
Linjie Li, Jie Lei, Zhe Gan +12
Most existing video-and-language (VidL) research focuses on a single dataset, or multiple datasets of a single task. In reality, a truly useful VidL system is expected to be easily…
Chasing Sparsity in Vision Transformers: An End-to-End Exploration
Tianlong Chen, Yu Cheng, Zhe Gan +3
Vision transformers (ViTs) have recently received explosive popularity, but their enormous model sizes and training costs remain daunting. Conventional post-training pruning often…
Adversarial VQA: A New Benchmark for Evaluating the Robustness of VQA Models
Linjie Li, Jie Lei, Zhe Gan +1
Benefiting from large-scale pre-training, we have witnessed significant performance boost on the popular Visual Question Answering (VQA) task. Despite rapid progress, it remains un…
CUPID: Adaptive Curation of Pre-training Data for Video-and-Language Representation Learning
Luowei Zhou, Jingjing Liu, Yu Cheng +2
This work concerns video-language pre-training and representation learning. In this now ubiquitous training scheme, a model first performs pre-training on paired videos and text (e…
Playing Lottery Tickets with Vision and Language
Zhe Gan, Yen-Chun Chen, Linjie Li +6
Large-scale pre-training has recently revolutionized vision-and-language (VL) research. Models such as LXMERT and UNITER have significantly lifted the state of the art over a wide…
Adversarial Feature Augmentation and Normalization for Visual Recognition
Tianlong Chen, Yu Cheng, Zhe Gan +4
Recent advances in computer vision take advantage of adversarial data augmentation to ameliorate the generalization ability of classification models. Here, we present an effective…
Improving Zero-shot Voice Style Transfer via Disentangled Representation Learning
Siyang Yuan, Pengyu Cheng, Ruiyi Zhang +3
Voice style transfer, also called voice conversion, seeks to modify one speaker's voice to generate speech as if it came from another (target) speaker. Previous works have made pro…
The Elastic Lottery Ticket Hypothesis
Xiaohan Chen, Yu Cheng, Shuohang Wang +3
Lottery Ticket Hypothesis (LTH) raises keen attention to identifying sparse trainable subnetworks, or winning tickets, which can be trained in isolation to achieve similar or even…
Data-Efficient GAN Training Beyond (Just) Augmentations: A Lottery Ticket Perspective
Tianlong Chen, Yu Cheng, Zhe Gan +2
Training generative adversarial networks (GANs) with limited real image data generally results in deteriorated performance and collapsed models. To conquer this challenge, we are i…
Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling
Jie Lei, Linjie Li, Luowei Zhou +4
The canonical approach to video-and-language learning (e.g., video question answering) dictates a neural model to learn from offline-extracted dense video features from vision mode…
EarlyBERT: Efficient BERT Training via Early-bird Lottery Tickets
Xiaohan Chen, Yu Cheng, Shuohang Wang +3
Heavily overparameterized language models such as BERT, XLNet and T5 have achieved impressive success in many NLP tasks. However, their high model complexity requires enormous comp…