829 citations · 936 across the 14 of their papers we have counts for
14 papers
Enriching Phrases with Coupled Pixel and Object Contexts for Panoptic Narrative Grounding
Tianrui Hui, Zihan Ding, Junshi Huang +5
Panoptic narrative grounding (PNG) aims to segment things and stuff objects in an image described by noun phrases of a narrative caption. As a multimodal task, an essential aspect…
DiT: Efficient Vision Transformers with Dynamic Token Routing
Yuchen Ma, Zhengcong Fei, Junshi Huang
Recently, the tokens of images share the same static data flow in many dense networks. However, challenges arise from the variance among the objects in images, such as large variat…
Gradient-Free Textual Inversion
Zhengcong Fei, Mingyuan Fan, Junshi Huang
Recent works on personalized text-to-image generation usually learn to bind a special token with specific subjects or styles of a few given images by tuning its embedding through g…
EfficientRep:An Efficient Repvgg-style ConvNets with Hardware-aware Neural Network Design
Kaiheng Weng, Xiangxiang Chu, Xiaoming Xu +2
We present a hardware-efficient architecture of convolutional neural network, which has a repvgg-like architecture. Flops or parameters are traditional metrics to evaluate the effi…
Uncertainty-Aware Image Captioning
Zhengcong Fei, Mingyuan Fan, Li Zhu +3
It is well believed that the higher uncertainty in a word of the caption, the more inter-correlated context information is required to determine it. However, current image captioni…
Meta-Ensemble Parameter Learning
Zhengcong Fei, Shuman Tian, Junshi Huang +2
Ensemble of machine learning models yields improved performance as well as robustness. However, their memory requirements and inference costs can be prohibitively high. Knowledge d…
Progressive Text-to-Image Generation
Zhengcong Fei, Mingyuan Fan, Li Zhu +1
Recently, Vector Quantized AutoRegressive (VQ-AR) models have shown remarkable results in text-to-image synthesis by equally predicting discrete image tokens from the top left to b…
PPMN: Pixel-Phrase Matching Network for One-Stage Panoptic Narrative Grounding
Zihan Ding, Zi-han Ding, Tianrui Hui +4
Panoptic Narrative Grounding (PNG) is an emerging task whose goal is to segment visual objects of things and stuff categories described by dense narrative captions of a still image…
Efficient Modeling of Future Context for Image Captioning
Zhengcong Fei, Junshi Huang, Xiaoming Wei +1
Existing approaches to image captioning usually generate the sentence word-by-word from left to right, with the constraint of conditioned on local context including the given image…
Language-Bridged Spatial-Temporal Interaction for Referring Video Object Segmentation
Zihan Ding, Tianrui Hui, Junshi Huang +3
Referring video object segmentation aims to predict foreground labels for objects referred by natural language expressions in videos. Previous methods either depend on 3D ConvNets…
Rethinking BiSeNet For Real-time Semantic Segmentation
Mingyuan Fan, Shenqi Lai, Junshi Huang +4
BiSeNet has been proved to be a popular two-stream network for real-time segmentation. However, its principle of adding an extra path to encode spatial information is time-consumin…
More is Less: A More Complicated Network with Less Inference Complexity
Xuanyi Dong, Junshi Huang, Yi Yang +1
In this paper, we present a novel and general network structure towards accelerating the inference process of convolutional neural networks, which is more complicated in network st…
Cross-domain Image Retrieval with a Dual Attribute-aware Ranking Network
Junshi Huang, Rogerio S. Feris, Qiang Chen +1
We address the problem of cross-domain image retrieval, considering the following practical application: given a user photo depicting a clothing image, our goal is to retrieve the…
CNN: Single-label to Multi-label
Yunchao Wei, Wei Xia, Junshi Huang +4
Convolutional Neural Network (CNN) has demonstrated promising performance in single-label image classification tasks. However, how CNN best copes with multi-label images still rema…