8 citations · 9 across the 4 of their papers we have counts for
4 papers
MMPlanner: Zero-Shot Multimodal Procedural Planning with Chain-of-Thought Object State Reasoning
Afrina Tabassum, Bin Guo, Xiyao Ma +2
Multimodal Procedural Planning (MPP) aims to generate step-by-step instructions that combine text and images, with the central challenge of preserving object-state consistency acro…
uaMix-MAE: Efficient Tuning of Pretrained Audio Transformers with Unsupervised Audio Mixtures
Afrina Tabassum, Dung Tran, Trung Dang +2
Masked Autoencoders (MAEs) learn rich low-level representations from unlabeled data but require substantial labeled data to effectively adapt to downstream tasks. Conversely, Insta…
Hard Negative Sampling Strategies for Contrastive Representation Learning
Afrina Tabassum, Muntasir Wahed, Hoda Eldardiry +1
One of the challenges in contrastive learning is the selection of appropriate \textit{hard negative} examples, in the absence of label information. Random sampling or importance sa…
Adversarial Contrastive Learning by Permuting Cluster Assignments
Muntasir Wahed, Afrina Tabassum, Ismini Lourentzou
Contrastive learning has gained popularity as an effective self-supervised representation learning technique. Several research directions improve traditional contrastive approaches…