Search Results for author:
Found 38 papers, 19 papers with code
Optimal Partial Transport Based Sentence Selection for Long-form Document Matching
Enjoying the partial transport properties of OPT, the selected key sentences can not only effectively enhance the matching accuracy, but also be explained as the rationales for the matching results.
Dynamic Prompt Optimizing for Text-to-Image Generation
Users assign weights or alter the injection time steps of certain words in the text prompts to improve the quality of generated images.
Domain-adaptive and Subgroup-specific Cascaded Temperature Regression for Out-of-distribution Calibration
Although deep neural networks yield high classification accuracy given sufficient training data, their predictions are typically overconfident or under-confident, i. e., the prediction confidences cannot truly reflect the accuracy.
Counterfactual Cross-modality Reasoning for Weakly Supervised Video Moment Localization
Finally, by suppressing the unimodal effect of masked query, we can rectify the reconstructions of video proposals to perform reasonable contrastive learning.
Zero-shot Skeleton-based Action Recognition via Mutual Information Estimation and Maximization
Specifically, 1) we maximize the MI between visual and semantic space for distribution alignment; 2) we leverage the temporal information for estimating the MI by encouraging MI to increase as more frames are observed.
Synthesizing Long-Term Human Motions with Diffusion Models via Coherent Sampling
Firstly, they cannot directly generate coherent motions and require additional operations such as interpolation to process the generated actions.
Spatio-Temporal Branching for Motion Prediction using Motion Increments
Human motion prediction (HMP) has emerged as a popular research topic due to its diverse applications, but it remains a challenging task due to the stochastic and aperiodic nature of future poses.
Atomic and Subgraph-aware Bilateral Aggregation for Molecular Representation Learning
In this paper, we introduce a new model for molecular representation learning called the Atomic and Subgraph-aware Bilateral Aggregation (ASBA), which addresses the limitations of previous atom-wise and subgraph-wise models by incorporating both types of information.
Toward Auto-evaluation with Confidence-based Category Relation-aware Regression
Auto-evaluation aims to automatically evaluate a trained model on any test dataset without human annotations.
Transfer Knowledge from Head to Tail: Uncertainty Calibration under Long-tailed Distribution
We adaptively transfer knowledge from head classes to get the target probability density of tail classes.
Self-supervised Action Representation Learning from Partial Spatio-Temporal Skeleton Sequences
Specifically, we construct a negative-sample-free triplet steam structure that is composed of an anchor stream without any masking, a spatial masking stream with Central Spatial Masking (CSM), and a temporal masking stream with Motion Attention Temporal Masking (MATM).
Statistical inference for the logarithmic spatial heteroskedasticity model with exogenous variables
For the log-SHE model, its spatial near-epoch dependence (NED) property is investigated, and a systematic statistical inference procedure is provided, including the maximum likelihood and generalized method of moments estimators, the Wald, Lagrange multiplier and likelihood-ratio-type D tests for model parameter constraints, and the overidentification test for the model diagnostic checking.
Exploring Temporal Concurrency for Video-Language Representation Learning
Paired video and language data is naturally temporal concurrency, which requires the modeling of the temporal dynamics within each modality and the temporal alignment across modalities simultaneously.
Modeling Video As Stochastic Processes for Fine-Grained Video Representation Learning
Specifically, we enforce the embeddings of the frame sequence of interest to approximate a goal-oriented stochastic process, i. e., Brownian bridge, in the latent space via a process-based contrastive loss.
MetaMask: Revisiting Dimensional Confounder for Self-Supervised Learning
As a successful approach to self-supervised learning, contrastive learning aims to learn invariant information shared among distortions of the input sample.
Modeling Multiple Views via Implicitly Preserving Global Consistency and Local Complementarity
To this end, we propose a methodology, specifically consistency and complementarity network (CoCoNet), which avails of strict global inter-view consistency and local cross-view complementarity preserving regularization to comprehensively learn representations from multiple views.
A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Language
Although artificial intelligence (AI) has made significant progress in understanding molecules in a wide range of fields, existing models generally acquire the single cognitive ability from the single molecular modality.
Ranked #7 on
Molecule Captioning
on ChEBI-20
Interventional Contrastive Learning with Meta Semantic Regularizer
Contrastive learning (CL)-based self-supervised learning models learn visual representations in a pairwise manner.
SemMAE: Semantic-Guided Masking for Learning Masked Autoencoders
In this paper, we explore a potential visual analogue of words, i. e., semantic parts, and we integrate semantic information into the training process of MAE by proposing a Semantic-Guided Masking strategy.
Do we really need temporal convolutions in action segmentation?
Most state-of-the-art methods focus on designing temporal convolution-based models, but the inflexibility of temporal convolutions and the difficulties in modeling long-term temporal dependencies restrict the potential of these models.
Ranked #1 on
Action Segmentation
on 50Salads
Supporting Vision-Language Model Inference with Causality-pruning Knowledge Prompt
Vision-language models are pre-trained by aligning image-text pairs in a common space so that the models can deal with open-set visual concepts by learning semantic information from textual labels.
Semi-WTC: A Practical Semi-supervised Framework for Attack Categorization through Weight-Task Consistency
In addition, to cope with new attacks in real-world deployment, we propose an Active Adaption Resampling (AAR) method, which can better discover the distribution of unseen sample data and adapt the parameters of encoder.
MetAug: Contrastive Learning via Meta Feature Augmentation
We perform a meta learning technique to build the augmentation generator that updates its network parameters by considering the performance of the encoder.
Robust Local Preserving and Global Aligning Network for Adversarial Domain Adaptation
We conduct theoretical analysis on the robustness of the proposed RLPGA and prove that the robust informative-theoretic-based loss and the local preserving module are beneficial to reduce the empirical risk of the target domain.
Preformer: Predictive Transformer with Multi-Scale Segment-wise Correlations for Long-Term Time Series Forecasting
In this way, if a key segment has a high correlation score with the query segment, its successive segment contributes more to the prediction of the query segment.
Temporal Alignment Prediction for Supervised Representation Learning and Few-Shot Sequence Classification
Explainable distances for sequence data depend on temporal alignment to tackle sequences with different lengths and local variances.
Log-Polar Space Convolution
Convolutional neural networks use regular quadrilateral convolution kernels to extract features.
Domain-Invariant Representation Learning with Global and Local Consistency
In this paper, we give an analysis of the existing representation learning framework of unsupervised domain adaptation and show that the learned feature representations of the source domain samples are with discriminability, compressibility, and transferability.
SCformer: Segment Correlation Transformer for Long Sequence Time Series Forecasting
Long-term time series forecasting is widely used in real-world applications such as financial investment, electricity management and production planning.
Sample-specific and Context-aware Augmentation for Long Tail Image Classification
We apply STG to samples of tail classes for augmentation in the classifier-tuning stage.
Information Theory-Guided Heuristic Progressive Multi-View Coding
To this end, we rethink the existing multi-view learning paradigm from the information theoretical perspective and then propose a novel information theoretical framework for generalized multi-view learning.
Log-Polar Space Convolution for Convolutional Neural Networks
Convolutional neural networks use regular quadrilateral convolution kernels to extract features.
Unsupervised Embedding Learning from Uncertainty Momentum Modeling
We justify that the performance limitation is caused by the gradient vanishing on these sample outliers.
Order-Preserving Wasserstein Discriminant Analysis
Supervised dimensionality reduction for sequence data projects the observations in sequences onto a low-dimensional subspace to better separate different sequence classes.
Learning Low-Dimensional Temporal Representations
Low-dimensional discriminative representations enhance machine learning methods in both performance and complexity, motivating supervised dimensionality reduction (DR) that transforms high-dimensional data to a discriminative subspace.
Easy Identification From Better Constraints: Multi-Shot Person Re-Identification From Reference Constraints
Multi-shot person re-identification (MsP-RID) utilizes multiple images from the same person to facilitate identification.
Order-Preserving Wasserstein Distance for Sequence Matching
We present a new distance measure between sequences that can tackle local temporal distortion and periodic sequences with arbitrary starting points.
Heteroscedastic Max-Min Distance Analysis
Many discriminant analysis methods such as LDA and HLDA actually maximize the average pairwise distances between classes, which often causes the class separation problem.
