Search Results for author:
Found 14 papers, 10 papers with code
VidLA: Video-Language Alignment at Scale
To effectively address this limitation, we instead keep the network architecture simple and use a set of data tokens that operate at different temporal resolutions in a hierarchical manner, accounting for the temporally hierarchical nature of videos.
Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled video
But are we making the best use of data?
CDFSL-V: Cross-Domain Few-Shot Learning for Videos
To address this issue, in this work, we propose a novel cross-domain few-shot video action recognition method that leverages self-supervised learning and curriculum learning to balance the information from the source and target domains.
cross-domain few-shot learning
Few-Shot action recognition
+3
Preserving Modality Structure Improves Multi-Modal Learning
Self-supervised learning on large-scale multi-modal datasets allows learning semantically meaningful embeddings in a joint multi-modal representation space without relying on human annotations.
TimeBalance: Temporally-Invariant and Temporally-Distinctive Video Representations for Semi-Supervised Action Recognition
We observe that these representations complement each other depending on the nature of the action.
SSDA: Secure Source-Free Domain Adaptation
Source-free domain adaptation (SFDA) is a popular unsupervised domain adaptation method where a pre-trained model from a source domain is adapted to a target domain without accessing any source data.
PivoTAL: Prior-Driven Supervision for Weakly-Supervised Temporal Action Localization
To address this, we present PivoTAL, Prior-driven Supervision for Weakly-supervised Temporal Action Localization, to approach WTAL from a localization-by-localization perspective by learning to localize the action snippets directly.
Weakly Supervised Action Localization
Weakly Supervised Temporal Action Localization
Towards Realistic Semi-Supervised Learning
We also highlight the flexibility of our approach in solving novel class discovery task, demonstrate its stability in dealing with imbalanced data, and complement our approach with a technique to estimate the number of novel classes
Ranked #1 on
Open-World Semi-Supervised Learning
on CIFAR-100
Novel Class Discovery
Open-World Semi-Supervised Learning
+1
OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning
In the open-world SSL problem, the objective is to recognize samples of known classes, and simultaneously detect and cluster samples belonging to novel classes present in unlabeled data.
Ranked #1 on
Open-World Semi-Supervised Learning
on CIFAR-10
UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learning
To combat label noise, recent state-of-the-art methods employ some sort of sample selection mechanism to select a possibly clean subset of data.
Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning
Equivariance or invariance has been employed standalone in the previous works; however, to the best of our knowledge, they have not been used jointly.
TCLR: Temporal Contrastive Learning for Video Representation
However, prior work on contrastive learning for video data has not explored the effect of explicitly encouraging the features to be distinct across the temporal dimension.
Ranked #9 on
Self-supervised Video Retrieval
on UCF101
In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning
The recent research in semi-supervised learning (SSL) is mostly dominated by consistency regularization based methods which achieve strong performance.
Gabriella: An Online System for Real-Time Activity Detection in Untrimmed Security Videos
For tubelet extraction, we propose a localization network which takes a video clip as input and spatio-temporally detects potential foreground regions at multiple scales to generate action tubelets.
