Search Results for author:
Found 5 papers, 0 papers with code
Two-stream joint matching method based on contrastive learning for few-shot action recognition
Although few-shot action recognition based on metric learning paradigm has achieved significant success, it fails to address the following issues: (1) inadequate action relation modeling and underutilization of multi-modal information; (2) challenges in handling video matching problems with different lengths and speeds, and video matching problems with misalignment of video sub-actions.
Multi-Stage Coarse-to-Fine Contrastive Learning for Conversation Intent Induction
The key to automatic intention induction is that, for any given set of new data, the sentence representation obtained by the model can be well distinguished from different labels.
Forcing the Whole Video as Background: An Adversarial Learning Strategy for Weakly Temporal Action Localization
With video-level labels, weakly supervised temporal action localization (WTAL) applies a localization-by-classification paradigm to detect and classify the action in untrimmed videos.
Classification
Weakly-supervised Temporal Action Localization
+1
Deep Domain Adaptation for Pavement Crack Detection
In this paper, we propose a Deep Domain Adaptation-based Crack Detection Network (DDACDN), which learns domain invariant features by taking advantage of the source domain knowledge to predict the multi-category crack location information in the target domain, where only image-level labels are available.
Face Recognition via Globality-Locality Preserving Projections
We present an improved Locality Preserving Projections (LPP) method, named Gloablity-Locality Preserving Projections (GLPP), to preserve both the global and local geometric structures of data.
