57 citations · 226 across the 36 of their papers we have counts for
11 papers · 2 filters
Label Semantic Knowledge Distillation for Unbiased Scene Graph Generation
Lin Li, Long Chen, Hanrong Shi +4
The Scene Graph Generation (SGG) task aims to detect all the objects and their pairwise visual relationships in a given image. Although SGG has achieved remarkable progress over th…
Integrating Object-aware and Interaction-aware Knowledge for Weakly Supervised Scene Graph Generation
Xingchen Li, Long Chen, Wenbo Ma +2
Recently, increasing efforts have been focused on Weakly Supervised Scene Graph Generation (WSSGG). The mainstream solution for WSSGG typically follows the same pipeline: they firs…
Unified Normalization for Accelerating and Stabilizing Transformers
Qiming Yang, Kai Zhang, Chaoxiang Lan +5
Solid results from Transformers have made them prevailing architectures in various natural language and vision tasks. As a default component in Transformers, Layer Normalization (L…
Rethinking the Evaluation of Unbiased Scene Graph Generation
Xingchen Li, Long Chen, Jian Shao +3
Current Scene Graph Generation (SGG) methods tend to predict frequent predicate categories and fail to recognize rare ones due to the severe imbalanced distribution of predicates.…
Rethinking the Reference-based Distinctive Image Captioning
Yangjun Mao, Long Chen, Zhihong Jiang +4
Distinctive Image Captioning (DIC) -- generating distinctive captions that describe the unique details of a target image -- has received considerable attention over the last few ye…
Explicit Image Caption Editing
Zhen Wang, Long Chen, Wenbo Ma +4
Given an image and a reference caption, the image caption editing task aims to correct the misalignment errors and generate a refined caption. However, all existing caption editing…
NICEST: Noisy Label Correction and Training for Robust Scene Graph Generation
Lin Li, Jun Xiao, Hanrong Shi +4
Nearly all existing scene graph generation (SGG) models have overlooked the ground-truth annotation qualities of mainstream SGG datasets, i.e., they assume: 1) all the manually ann…
Rethinking Data Augmentation for Robust Visual Question Answering
Long Chen, Yuhang Zheng, Jun Xiao
Data Augmentation (DA) -- generating extra training samples beyond original training set -- has been widely-used in today's unbiased VQA models to mitigate the language biases. Cur…
The Devil is in the Labels: Noisy Label Correction for Robust Scene Graph Generation
Lin Li, Long Chen, Yifeng Huang +3
Unbiased SGG has achieved significant progress over recent years. However, almost all existing SGG models have overlooked the ground-truth annotation qualities of prevailing SGG da…
Rethinking Multi-Modal Alignment in Video Question Answering from Feature and Sample Perspectives
Shaoning Xiao, Long Chen, Kaifeng Gao +4
Reasoning about causal and temporal event relations in videos is a new destination of Video Question Answering (VideoQA).The major stumbling block to achieve this purpose is the se…
Bidirectional Self-Training with Multiple Anisotropic Prototypes for Domain Adaptive Semantic Segmentation
Yulei Lu, Yawei Luo, Li Zhang +3
A thriving trend for domain adaptive segmentation endeavors to generate the high-quality pseudo labels for target domain and retrain the segmentor on them. Under this self-training…