Search Results for author:
Found 41 papers, 15 papers with code
Simultaneous Detection and Interaction Reasoning for Object-Centric Action Recognition
Existing methods usually adopt a two-stage pipeline, where object proposals are first detected using a pretrained detector, and then are fed to an action recognition model for extracting video features and learning the object relations for action recognition.
Tuning-Free Adaptive Style Incorporation for Structure-Consistent Text-Driven Style Transfer
In this work, we propose a novel solution to the text-driven style transfer task, namely, Adaptive Style Incorporation~(ASI), to achieve fine-grained feature-level style incorporation.
SSR: SAM is a Strong Regularizer for domain adaptive semantic segmentation
We introduced SSR, which utilizes SAM (segment-anything) as a strong regularizer during training, to greatly enhance the robustness of the image encoder for handling various domains.
Beyond Prototypes: Semantic Anchor Regularization for Better Representation Learning
By pulling the learned features to these semantic anchors, several advantages can be attained: 1) the intra-class compactness and naturally inter-class separability, 2) induced bias or errors from feature learning can be avoided, and 3) robustness to the long-tailed problem.
Multi-modal Instance Refinement for Cross-domain Action Recognition
In the source domain, some training samples are of low-relevance to target domain due to the difference in viewpoints, action styles, etc.
High-level Feature Guided Decoding for Semantic Segmentation
One crucial design of the HFG is to protect the high-level features from being contaminated by using proper stop-gradient operations so that the backbone does not update according to the noisy gradient from the upsampler.
CARD: Semantic Segmentation with Efficient Class-Aware Regularized Decoder
Extensive experiments and ablation studies conducted on multiple benchmark datasets demonstrate that the proposed CAR can boost the accuracy of all baseline models by up to 2. 23% mIOU with superior generalization ability.
Harmonious Teacher for Cross-Domain Object Detection
Self-training approaches recently achieved promising results in cross-domain object detection, where people iteratively generate pseudo labels for unlabeled target domain samples with a model, and select high-confidence samples to refine the model.
Minimizing Maximum Model Discrepancy for Transferable Black-box Targeted Attacks
On the algorithmic side, we derive a new algorithm for black-box targeted attacks based on our theoretical analysis, in which we additionally minimize the maximum model discrepancy(M3D) of the substitute models when training the generator to generate adversarial examples.
Multi-rater Prism: Learning self-calibrated medical image segmentation from multiple raters
In this paper, we propose a novel neural network framework, called Multi-Rater Prism (MrPrism) to learn the medical image segmentation from multiple labels.
Motion and Appearance Adaptation for Cross-Domain Motion Transfer
Motion transfer aims to transfer the motion of a driving video to a source image.
Motion Transformer for Unsupervised Image Animation
Image animation aims to animate a source image by using motion learned from a driving video.
Calibrate the inter-observer segmentation uncertainty via diagnosis-first principle
Inspired by this observation, we propose diagnosis-first principle, which is to take disease diagnosis as the criterion to calibrate the inter-observer segmentation uncertainty.
Cross-domain Detection Transformer based on Spatial-aware and Semantic-aware Token Alignment
In particular, we take advantage of the characteristics of cross-attention as used in detection transformer and propose the spatial-aware token alignment (SpaTA) and the semantic-aware token alignment (SemTA) strategies to guide the token alignment across domains.
Undoing the Damage of Label Shift for Cross-domain Semantic Segmentation
Existing works typically treat cross-domain semantic segmentation (CDSS) as a data distribution mismatch problem and focus on aligning the marginal distribution or conditional distribution.
Structure-Aware Motion Transfer with Deformable Anchor Model
Specifically, inspired by the known deformable part model (DPM), our DAM introduces two types of anchors or keypoints: i) a number of motion anchors that capture both appearance and motion information from the source image and driving video; ii) a latent root anchor, which is linked to the motion anchors to facilitate better learning of the representations of the object structure information.
Learning Pixel-Level Distinctions for Video Highlight Detection
To this end, we propose to learn pixel-level distinctions to improve the video highlight detection.
Diverse Preference Augmentation with Multiple Domains for Cold-start Recommendations
Motivated by the idea of meta-augmentation, in this paper, by treating a user's preference over items as a task, we propose a so-called Diverse Preference Augmentation framework with multiple source domains based on meta-learning (referred to as MetaDPA) to i) generate diverse ratings in a new domain of interest (known as target domain) to handle overfitting on the case of sparse interactions, and to ii) learn a preference model in the target domain via a meta-learning scheme to alleviate cold-start issues.
Move As You Like: Image Animation in E-Commerce Scenario
Creative image animations are attractive in e-commerce applications, where motion transfer is one of the import ways to generate animations from static images.
Counterfactual Debiasing Inference for Compositional Action Recognition
By doing that, our proposed CDN method can better recognize unseen action instances by debiasing the effect of appearances.
Progressive Modality Reinforcement for Human Multimodal Emotion Recognition From Unaligned Multimodal Sequences
In turn, it also collects the reinforced features from each modality and uses them to generate a reinforced common message.
Real-Time Video Super-Resolution on Smartphones with Deep Learning, Mobile AI 2021 Challenge: Report
Video super-resolution has recently become one of the most important mobile-related problems due to the rise of video communication and streaming services.
BAPA-Net: Boundary Adaptation and Prototype Alignment for Cross-Domain Semantic Segmentation
By integrating the boundary adaptation and prototype alignment, we are able to train a discriminative and domain-invariant model for cross-domain semantic segmentation.
Collaborative Generative Hashing for Marketing and Fast Cold-start Recommendation
Cold-start has being a critical issue in recommender systems with the explosion of data in e-commerce.
Region Comparison Network for Interpretable Few-shot Image Classification
For that, in this work, we propose a metric learning based method named Region Comparison Network (RCN), which is able to reveal how few-shot learning works as in a neural network as well as to find out specific regions that are related to each other in images coming from the query and support sets.
Ranked #33 on
Few-Shot Image Classification
on CIFAR-FS 5-way (5-shot)
Dynamic and Static Context-aware LSTM for Multi-agent Motion Prediction
Existing work addressed this challenge by either learning social spatial interactions represented by the positions of a group of pedestrians, while ignoring their temporal coherence (\textit{i. e.} dependencies between different long trajectories), or by understanding the complicated scene layout (\textit{e. g.} scene segmentation) to ensure safe navigation.
Reconstruction Regularized Deep Metric Learning for Multi-label Image Classification
In this paper, we present a novel deep metric learning method to tackle the multi-label image classification problem.
Deeply Aligned Adaptation for Cross-domain Object Detection
Cross-domain object detection has recently attracted more and more attention for real-world applications, since it helps build robust detectors adapting well to new environments.
Learning Cross-domain Semantic-Visual Relationships for Transductive Zero-Shot Learning
Zero-Shot Learning (ZSL) learns models for recognizing new classes.
Unbiased Mean Teacher for Cross-domain Object Detection
We reveal that there often exists a considerable model bias for the simple mean teacher (MT) model in cross-domain scenarios, and eliminate the model bias with several simple yet highly effective strategies.
Collaborative Generated Hashing for Market Analysis and Fast Cold-start Recommendation
Cold-start and efficiency issues of the Top-k recommendation are critical to large-scale recommender systems.
Open-Ended Visual Question Answering by Multi-Modal Domain Adaptation
A straightforward solution is to fine-tune a pre-trained source model by using those limited labeled target data, but it usually cannot work well due to the considerable difference between the data distributions of the source and target domains.
Constructing Self-motivated Pyramid Curriculums for Cross-Domain Semantic Segmentation: A Non-Adversarial Approach
We propose a new approach, called self-motivated pyramid curriculum domain adaptation (PyCDA), to facilitate the adaptation of semantic segmentation neural networks from synthetic source domains to real target domains.
Ranked #14 on
Image-to-Image Translation
on SYNTHIA-to-Cityscapes
Adversarial Multimodal Network for Movie Question Answering
In AMN, as inspired by generative adversarial networks, we propose to learn multimodal feature representations by finding a more coherent subspace for video clips and the corresponding texts (e. g., subtitles and questions).
Domain Adversarial Reinforcement Learning for Partial Domain Adaptation
In this more general and practical scenario, a major challenge is how to select source instances in the shared classes across different domains for positive transfer.
Known-class Aware Self-ensemble for Open Set Domain Adaptation
Particularly, in open set domain adaptation, we allow the classes from the source and target domains to be partially overlapped.
MiniMax Entropy Network: Learning Category-Invariant Features for Domain Adaptation
Unlike most existing approaches which employ a generator to deal with domain difference, MMEN focuses on learning the categorical information from unlabeled target samples with the help of labeled source samples.
Learning Transferable Self-attentive Representations for Action Recognition in Untrimmed Videos with Weak Supervision
Action recognition in videos has attracted a lot of attention in the past decade.
Exploiting Images for Video Recognition with Hierarchical Generative Adversarial Networks
By taking advantage of these two-level adversarial learning, our method is capable of learning a domain-invariant feature representation of source images and target videos.
Recurrent Image Captioner: Describing Images with Spatial-Invariant Transformation and Attention Filtering
Along with the prosperity of recurrent neural network in modelling sequential data and the power of attention mechanism in automatically identify salient information, image captioning, a. k. a., image description, has been remarkably advanced in recent years.
Event Recognition in Videos by Learning from Heterogeneous Web Sources
In this work, we propose to leverage a large number of loosely labeled web videos (e. g., from YouTube) and web images (e. g., from Google/Bing image search) for visual event recognition in consumer videos without requiring any labeled consumer videos.
