283 citations · 456 across the 11 of their papers we have counts for
10 papers · 1 filter
SINC: Self-Supervised In-Context Learning for Vision-Language Tasks
Yi-Syuan Chen, Yun-Zhu Song, Cheng Yu Yeo +3
Large Pre-trained Transformers exhibit an intriguing capacity for in-context learning. Without gradient updates, these models can rapidly construct new predictors from demonstratio…
Exploring Anchor-based Detection for Ego4D Natural Language Query
Sipeng Zheng, Qi Zhang, Bei Liu +2
In this paper we provide the technique report of Ego4D natural language query challenge in CVPR 2022. Natural language query task is challenging due to the requirement of comprehen…
Reference-based Defect Detection Network
Zhaoyang Zeng, Bei Liu, Jianlong Fu +1
The defect detection task can be regarded as a realistic scenario of object detection in the computer vision field and it is widely used in the industrial field. Directly applying…
Probing Inter-modality: Visual Parsing with Self-Attention for Vision-Language Pre-training
Hongwei Xue, Yupan Huang, Bei Liu +4
Vision-Language Pre-training (VLP) aims to learn multi-modal representations from image-text pairs and serves for downstream vision-language tasks in a fine-tuning fashion. The dom…
Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning
Zhicheng Huang, Zhaoyang Zeng, Yupan Huang +3
We study joint learning of Convolutional Neural Network (CNN) and Transformer for vision-language pre-training (VLPT) which aims to learn cross-modal alignments from millions of im…
Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Transformers
Zhicheng Huang, Zhaoyang Zeng, Bei Liu +2
We propose Pixel-BERT to align image pixels with text by deep multi-modal transformers that jointly learn visual and language embedding in a unified end-to-end framework. We aim to…
Learning Rich Image Region Representation for Visual Question Answering
Bei Liu, Zhicheng Huang, Zhaoyang Zeng +2
We propose to boost VQA by leveraging more powerful feature extractors by improving the representation ability of both visual and text features and the ensemble of models. For visu…
WSOD^2: Learning Bottom-up and Top-down Objectness Distillation for Weakly-supervised Object Detection
Zhaoyang Zeng, Bei Liu, Jianlong Fu +2
We study on weakly-supervised object detection (WSOD) which plays a vital role in relieving human involvement from object-level annotations. Predominant works integrate region prop…
Activitynet 2019 Task 3: Exploring Contexts for Dense Captioning Events in Videos
Shizhe Chen, Yuqing Song, Yida Zhao +5
Contextual reasoning is essential to understand events in long untrimmed videos. In this work, we systematically explore different captioning models with various contexts for the d…
Beyond Narrative Description: Generating Poetry from Images by Multi-Adversarial Training
Bei Liu, Jianlong Fu, Makoto P. Kato +1
Automatic generation of natural language from images has attracted extensive attention. In this paper, we take one step further to investigate generation of poetic language (with m…