1.1k citations · 4.4k across the 93 of their papers we have counts for
98 papers
Fine-Grained VR Sketching: Dataset and Insights
Ling Luo, Yulia Gryaditskaya, Yongxin Yang +2
We present the first fine-grained dataset of 1,497 3D VR sketch and 3D shape pairs of a chair category with large shapes diversity. Our dataset supports the recent trend in the ske…
Towards 3D VR-Sketch to 3D Shape Retrieval
Ling Luo, Yulia Gryaditskaya, Yongxin Yang +2
Growing free online 3D shapes collections dictated research on 3D retrieval. Active debate has however been had on (i) what the best input modality is to trigger retrieval, and (ii…
Doodle It Yourself: Class Incremental Learning by Drawing a Few Sketches
Ayan Kumar Bhunia, Viswanatha Reddy Gajjala, Subhadeep Koley +4
The human visual system is remarkable in learning new visual concepts from just a few examples. This is precisely the goal behind few-shot class incremental learning (FSCIL), where…
Partially Does It: Towards Scene-Level FG-SBIR with Partial Input
Pinaki Nath Chowdhury, Ayan Kumar Bhunia, Viswanatha Reddy Gajjala +3
We scrutinise an important observation plaguing scene-level sketch research -- that a significant portion of scene sketches are "partial". A quick pilot study reveals: (i) a scene…
Sketch3T: Test-Time Training for Zero-Shot SBIR
Aneeshan Sain, Ayan Kumar Bhunia, Vaishnav Potlapalli +3
Zero-shot sketch-based image retrieval typically asks for a trained model to be applied as is to unseen categories. In this paper, we question to argue that this setup by definitio…
Dynamic Instance Domain Adaptation
Zhongying Deng, Kaiyang Zhou, Da Li +3
Most existing studies on unsupervised domain adaptation (UDA) assume that each domain's training samples come with domain labels (e.g., painting, photo). Samples from each domain a…
FS-COCO: Towards Understanding of Freehand Sketches of Common Objects in Context
Pinaki Nath Chowdhury, Aneeshan Sain, Ayan Kumar Bhunia +3
We advance sketch research to scenes with the first dataset of freehand scene sketches, FS-COCO. With practical applications in mind, we collect sketches that convey scene content…
One Sketch for All: One-Shot Personalized Sketch Segmentation
Anran Qi, Yulia Gryaditskaya, Tao Xiang +1
We present the first one-shot personalized sketch segmentation method. We aim to segment all sketches belonging to the same category provisioned with a single sketch with a given p…
Domain Attention Consistency for Multi-Source Domain Adaptation
Zhongying Deng, Kaiyang Zhou, Yongxin Yang +1
Most existing multi-source domain adaptation (MSDA) methods minimize the distance between multiple source-target domain pairs via feature distribution alignment, an approach borrow…
Text-Based Person Search with Limited Data
Xiao Han, Sen He, Li Zhang +1
Text-based person search (TBPS) aims at retrieving a target person from an image gallery with a descriptive text query. Solving such a fine-grained cross-modal retrieval task is ch…
Few-Shot Temporal Action Localization with Query Adaptive Transformer
Sauradip Nag, Xiatian Zhu, Tao Xiang
Existing temporal action localization (TAL) works rely on a large number of training videos with exhaustive segment-level annotation, preventing them from scaling to new classes. A…
SOFT: Softmax-free Transformer with Linear Complexity
Jiachen Lu, Jinghan Yao, Junge Zhang +6
Vision transformers (ViTs) have pushed the state-of-the-art for various visual recognition tasks by patch-wise image tokenization followed by self-attention. However, the employmen…
One Loss for All: Deep Hashing with a Single Cosine Similarity based Learning Objective
Jiun Tian Hoe, Kam Woh Ng, Tianyu Zhang +3
A deep hashing model typically has two main learning objectives: to make the learned binary hash codes discriminative and to minimize a quantization error. With further constraints…
Disentangled Lifespan Face Synthesis
Sen He, Wentong Liao, Michael Ying Yang +3
A lifespan face synthesis (LFS) model aims to generate a set of photo-realistic face images of a person's whole life, given only one snapshot as reference. The generated face image…
Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer
Zhihe Lu, Sen He, Xiatian Zhu +3
A few-shot semantic segmentation model is typically composed of a CNN encoder, a CNN decoder and a simple classifier (separating foreground and background pixels). Most existing me…
Global Aggregation then Local Distribution for Scene Parsing
Xiangtai Li, Li Zhang, Guangliang Cheng +4
Modelling long-range contextual relationships is critical for pixel-wise prediction tasks such as semantic segmentation. However, convolutional neural networks (CNNs) are inherentl…
MixStyle Neural Networks for Domain Generalization and Adaptation
Kaiyang Zhou, Yongxin Yang, Yu Qiao +1
Neural networks do not generalize well to unseen data with domain shifts -- a longstanding problem in machine learning and AI. To overcome the problem, we propose MixStyle, a simpl…
Domain Generalization with MixStyle
Kaiyang Zhou, Yongxin Yang, Yu Qiao +1
Though convolutional neural networks (CNNs) have demonstrated remarkable ability in learning discriminative features, they often generalize poorly to unseen domains. Domain general…
StyleMeUp: Towards Style-Agnostic Sketch-Based Image Retrieval
Aneeshan Sain, Ayan Kumar Bhunia, Yongxin Yang +2
Sketch-based image retrieval (SBIR) is a cross-modal matching problem which is typically solved by learning a joint embedding space where the semantic content shared between photo…
Cloud2Curve: Generation and Vectorization of Parametric Sketches
Ayan Das, Yongxin Yang, Timothy Hospedales +2
Analysis of human sketches in deep learning has advanced immensely through the use of waypoint-sequences rather than raster-graphic representations. We further aim to model sketche…
More Photos are All You Need: Semi-Supervised Learning for Fine-Grained Sketch Based Image Retrieval
Ayan Kumar Bhunia, Pinaki Nath Chowdhury, Aneeshan Sain +3
A fundamental challenge faced by existing Fine-Grained Sketch-Based Image Retrieval (FG-SBIR) models is the data scarcity -- model performances are largely bottlenecked by the lack…
Vectorization and Rasterization: Self-Supervised Learning for Sketch and Handwriting
Ayan Kumar Bhunia, Pinaki Nath Chowdhury, Yongxin Yang +3
Self-supervised learning has gained prominence due to its efficacy at learning powerful representations from unlabelled data that achieve excellent performance on many challenging…
Context-Aware Layout to Image Generation with Enhanced Object Appearance
Sen He, Wentong Liao, Michael Ying Yang +4
A layout to image (L2I) generation model aims to generate a complicated image containing multiple objects (things) against natural background (stuff), conditioned on a given layout…
Domain Generalization: A Survey
Kaiyang Zhou, Ziwei Liu, Yu Qiao +2
Generalization to out-of-distribution (OOD) data is a capability natural to humans yet challenging for machines to reproduce. This is because most learning algorithms strongly rely…