Search Results for author:
Found 10 papers, 1 papers with code
LoRAP: Transformer Sub-Layers Deserve Differentiated Structured Compression for Large Language Models
With this regard, we design a mixed compression model, which organically combines Low-Rank matrix approximation And structured Pruning (LoRAP).
Cross-Stream Contrastive Learning for Self-Supervised Skeleton-Based Action Recognition
Besides, to further exploit the potential of positive pairs and increase the robustness of self-supervised representation learning, we propose a Positive Feature Transformation (PFT) strategy which adopts feature-level manipulation to increase the variance of positive pairs.
Cross-Domain Label Propagation for Domain Adaptation with Discriminative Graph Self-Learning
In this paper, we propose a novel domain adaptation method, which infers target pseudo-labels through cross-domain label propagation, such that the underlying manifold structure of two domain data can be explored.
Constrained Maximum Cross-Domain Likelihood for Domain Generalization
Finally, a Constrained Maximum Cross-domain Likelihood (CMCL) optimization problem is deduced, by solving which the joint distributions are naturally aligned.
Mitigating Both Covariate and Conditional Shift for Domain Generalization
Domain generalization (DG) aims to learn a model on several source domains, hoping that the model can generalize well to unseen target domains.
Active Learning with Effective Scoring Functions for Semi-Supervised Temporal Action Localization
And the other introduces a new metric based on mutual information between adjacent action proposals and evaluates the informativeness of video samples, named Temporal Context Inconsistency (TCI).
Attentive pooling for Group Activity Recognition
However, the existing methods simply employed max/average pooling in this framework, which ignored the distinct contributions of different individuals to the group activity recognition.
Deep Multi-View Semi-Supervised Clustering with Sample Pairwise Constraints
Multi-view clustering has attracted much attention thanks to the capacity of multi-source information integration.
Multi-scale 2D Representation Learning for weakly-supervised moment retrieval
Specifically, we first construct a two-dimensional map for each temporal scale to capture the temporal dependencies between candidates.
Domain Adaptation by Class Centroid Matching and Local Manifold Self-Learning
Domain adaptation has been a fundamental technology for transferring knowledge from a source domain to a target domain.
