675 citations · 1.7k across the 27 of their papers we have counts for
23 papers · 1 filter
Freestyle Layout-to-Image Synthesis
Han Xue, Zhiwu Huang, Qianru Sun +2
Typical layout-to-image synthesis (LIS) models generate images for a closed set of semantic classes, e.g., 182 common objects in COCO-Stuff. In this work, we explore the freestyle…
Extracting Class Activation Maps from Non-Discriminative Features as well
Zhaozheng Chen, Qianru Sun
Extracting class activation maps (CAM) from a classification model often results in poor coverage on foreground objects, i.e., only the discriminative region (e.g., the "head" of "…
Efficient Cross-Modal Video Retrieval with Meta-Optimized Frames
Ning Han, Xun Yang, Ee-Peng Lim +2
Cross-modal video retrieval aims to retrieve the semantically relevant videos given a text as a query, and is one of the fundamental tasks in Multimedia. Most of top-performing met…
On Mitigating Hard Clusters for Face Clustering
Yingjie Chen, Huasong Zhong, Chong Chen +5
Face clustering is a promising way to scale up face recognition systems using large-scale unlabeled face images. It remains challenging to identify small or sparse face image clust…
A Large-Scale Benchmark for Food Image Segmentation
Xiongwei Wu, Xin Fu, Ying Liu +3
Food image segmentation is a critical and indispensible task for developing health-related applications such as estimating food calories and nutrients. Existing food image segmenta…
Counterfactual Zero-Shot and Open-Set Visual Recognition
Zhongqi Yue, Tan Wang, Hanwang Zhang +2
We present a novel counterfactual framework for both Zero-Shot Learning (ZSL) and Open-Set Recognition (OSR), whose common challenge is generalizing to the unseen-classes by only t…
Causal Intervention for Weakly-Supervised Semantic Segmentation
Dong Zhang, Hanwang Zhang, Jinhui Tang +2
We present a causal inference framework to improve Weakly-Supervised Semantic Segmentation (WSSS). Specifically, we aim to generate better pixel-level pseudo-masks by using only im…
Feature Pyramid Transformer
Dong Zhang, Hanwang Zhang, Jinhui Tang +3
Feature interactions across space and scales underpin modern visual recognition systems because they introduce beneficial visual contexts. Conventionally, spatial contexts are pass…
Visual Commonsense R-CNN
Tan Wang, Jianqiang Huang, Hanwang Zhang +1
We present a novel unsupervised feature representation learning method, Visual Commonsense Region-based Convolutional Neural Network (VC R-CNN), to serve as an improved visual regi…
Mnemonics Training: Multi-Class Incremental Learning without Forgetting
Yaoyao Liu, Yuting Su, An-An Liu +2
Multi-Class Incremental Learning (MCIL) aims to learn new concepts by incrementally updating a model trained on previous concepts. However, there is an inherent trade-off to effect…
Meta-Transfer Learning through Hard Tasks
Qianru Sun, Yaoyao Liu, Zhaozheng Chen +2
Meta-learning has been proposed as a framework to address the challenging few-shot learning setting. The key idea is to leverage a large number of similar few-shot tasks in order t…
Joint Visual Grounding with Language Scene Graphs
Daqing Liu, Hanwang Zhang, Zheng-Jun Zha +2
Visual grounding is a task to ground referring expressions in images, e.g., localize "the white truck in front of the yellow one". To resolve this task fundamentally, the model sho…
Learning to Self-Train for Semi-Supervised Few-Shot Classification
Xinzhe Li, Qianru Sun, Yaoyao Liu +4
Few-shot classification (FSC) is challenging due to the scarcity of labeled training data (e.g. only one labeled data point per class). Meta-learning has shown to achieve promising…
A Novel BiLevel Paradigm for Image-to-Image Translation
Liqian Ma, Qianru Sun, Bernt Schiele +1
Image-to-image (I2I) translation is a pixel-level mapping that requires a large number of paired training data and often suffers from the problems of high diversity and strong cate…
An Ensemble of Epoch-wise Empirical Bayes for Few-shot Learning
Yaoyao Liu, Bernt Schiele, Qianru Sun
Few-shot learning aims to train efficient predictive models with a few examples. The lack of training data leads to poor models that perform high-variance or low-confidence predict…
Learning a Disentangled Embedding for Monocular 3D Shape Retrieval and Pose Estimation
Kyaw Zaw Lin, Weipeng Xu, Qianru Sun +2
We propose a novel approach to jointly perform 3D shape retrieval and pose estimation from monocular images.In order to make the method robust to real-world image variations, e.g.…
Meta-Transfer Learning for Few-Shot Learning
Qianru Sun, Yaoyao Liu, Tat-Seng Chua +1
Meta-learning has been proposed as a framework to address the challenging few-shot learning setting. The key idea is to leverage a large number of similar few-shot tasks in order t…
A Hybrid Model for Identity Obfuscation by Face Replacement
Qianru Sun, Ayush Tewari, Weipeng Xu +3
As more and more personal photos are shared and tagged in social media, avoiding privacy risks such as unintended recognition becomes increasingly challenging. We propose a new hyb…
Disentangled Person Image Generation
Liqian Ma, Qianru Sun, Stamatios Georgoulis +3
Generating novel, yet realistic, images of persons is a challenging task due to the complex interplay between the different image factors, such as the foreground, background and po…
Natural and Effective Obfuscation by Head Inpainting
Qianru Sun, Liqian Ma, Seong Joon Oh +3
As more and more personal photos are shared online, being able to obfuscate identities in such photos is becoming a necessity for privacy protection. People have largely resorted t…
Pose Guided Person Image Generation
Liqian Ma, Xu Jia, Qianru Sun +3
This paper proposes the novel Pose Guided Person Generation Network (PG) that allows to synthesize person images in arbitrary poses, based on an image of that person and a nove…
A Domain Based Approach to Social Relation Recognition
Qianru Sun, Bernt Schiele, Mario Fritz
Social relations are the foundation of human daily life. Developing techniques to analyze such relations from visual data bears great potential to build machines that better unders…
Orientation Driven Bag of Appearances for Person Re-identification
Liqian Ma, Hong Liu, Liang Hu +2
Person re-identification (re-id) consists of associating individual across camera network, which is valuable for intelligent video surveillance and has drawn wide attention. Althou…