Search Results for author:
Found 17 papers, 13 papers with code
Explicit Visual Prompting for Low-Level Structure Segmentations
Different from the previous visual prompting which is typically a dataset-level implicit embedding, our key insight is to enforce the tunable parameters focusing on the explicit visual content from each individual image, i. e., the features from frozen patch embeddings and the input's high-frequency components.
T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations
Additionally, we conduct analyses on HumanML3D and observe that the dataset size is a limitation of our approach.
Ranked #1 on
Motion Synthesis
on HumanML3D
SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation
We present SadTalker, which generates 3D motion coefficients (head pose, expression) of the 3DMM from audio and implicitly modulates a novel 3D-aware face render for talking head generation.
TokenCut: Segmenting Objects in Images and Videos with Self-supervised Transformer and Normalized Cut
This method also achieves competitive results for unsupervised video object segmentation tasks with the DAVIS, SegTV2, and FBMS datasets.
Jigsaw-ViT: Learning Jigsaw Puzzles in Vision Transformer
In this paper, we explore solving jigsaw puzzle as a self-supervised auxiliary loss in ViT for image classification, named Jigsaw-ViT.
Ranked #1 on
Learning with noisy labels
on ANIMAL
Back to MLP: A Simple Baseline for Human Motion Prediction
This paper tackles the problem of human motion prediction, consisting in forecasting future body poses from historically observed sequences.
Compressing Features for Learning with Noisy Labels
This decomposition provides three insights: (i) it shows that over-fitting is indeed an issue for learning with noisy labels; (ii) through an information bottleneck formulation, it explains why the proposed feature compression helps in combating label noise; (iii) it gives explanations on the performance boost brought by incorporating compression regularization into Co-teaching.
Ranked #7 on
Learning with noisy labels
on ANIMAL
Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut
For unsupervised saliency detection, we improve IoU for 4. 9%, 5. 2%, 12. 9% on ECSSD, DUTS, DUT-OMRON respectively compared to previous state of the art.
Ranked #1 on
Weakly-Supervised Object Localization
on CUB-200-2011
(Top-1 Localization Accuracy metric)
Re-ranking for image retrieval and transductive few-shot classification
In the problems of image retrieval and few-shot classification, the mainstream approaches focus on learning a better feature representation.
Learning Co-segmentation by Segment Swapping for Retrieval and Discovery
The goal of this work is to efficiently identify visually similar patterns in images, e. g. identifying an artwork detail copied between an engraving and an oil painting, or recognizing parts of a night-time photograph visible in its daytime counterpart.
Image Collation: Matching illustrations in manuscripts
For an historian, the first step in studying their evolution in a corpus of similar manuscripts is to identify which ones correspond to each other.
Boosting Co-teaching with Compression Regularization for Label Noise
On Clothing1M, our approach obtains 74. 9% accuracy which is slightly better than that of DivideMix.
Ranked #10 on
Image Classification
on Clothing1M
(using extra training data)
Empirical Bayes Transductive Meta-Learning with Synthetic Gradients
The evidence lower bound of the marginal log-likelihood of empirical Bayes decomposes as a sum of local KL divergences between the variational posterior and the true posterior on the query set of each task.
Ranked #11 on
Few-Shot Image Classification
on CIFAR-FS 5-way (1-shot)
RANSAC-Flow: generic two-stage image alignment
Coarse alignment is performed using RANSAC on off-the-shelf deep features.
Large-Scale Historical Watermark Recognition: dataset and a new consistency-based approach
Historical watermark recognition is a highly practical, yet unsolved challenge for archivists and historians.
Marginalized Average Attentional Network for Weakly-Supervised Learning
The MAAN employs a novel marginalized average aggregation (MAA) module and learns a set of latent discriminative probabilities in an end-to-end fashion.
Ranked #7 on
Weakly Supervised Action Localization
on ActivityNet-1.3
(mAP@0.5 metric)
Weakly Supervised Action Localization
Weakly-supervised Learning
+2
Discovering Visual Patterns in Art Collections with Spatially-consistent Feature Learning
Our goal in this paper is to discover near duplicate patterns in large collections of artworks.
