Delving into masked autoencoders for multi-label thorax disease classification
Abstract Vision Transformer (ViT) has become one of the most popular neural architectures
due to its simplicity, scalability, and compelling performance in multiple vision tasks …
due to its simplicity, scalability, and compelling performance in multiple vision tasks …
Mgmae: Motion guided masking for video masked autoencoding
Masked autoencoding has shown excellent performance on self-supervised video
representation learning. Temporal redundancy has led to a high masking ratio and …
representation learning. Temporal redundancy has led to a high masking ratio and …
Mart: Masked affective representation learning via masked temporal distribution distillation
Limited training data is a long-standing problem for video emotion analysis (VEA). Existing
works leverage the power of large-scale image datasets for transferring while failing to …
works leverage the power of large-scale image datasets for transferring while failing to …
Selective structured state-spaces for long-form video understanding
Effective modeling of complex spatiotemporal dependencies in long-form videos remains an
open problem. The recently proposed Structured State-Space Sequence (S4) model with its …
open problem. The recently proposed Structured State-Space Sequence (S4) model with its …
Audiovisual masked autoencoders
Can we leverage the audiovisual information already present in video to improve self-
supervised representation learning? To answer this question, we study various pretraining …
supervised representation learning? To answer this question, we study various pretraining …
Masked relation learning for deepfake detection
DeepFake detection aims to differentiate falsified faces from real ones. Most approaches
formulate it as a binary classification problem by solely mining the local artifacts and …
formulate it as a binary classification problem by solely mining the local artifacts and …
Multi-view masked world models for visual robotic manipulation
Visual robotic manipulation research and applications often use multiple cameras, or views,
to better perceive the world. How else can we utilize the richness of multi-view data? In this …
to better perceive the world. How else can we utilize the richness of multi-view data? In this …
Segment any point cloud sequences by distilling vision foundation models
Recent advancements in vision foundation models (VFMs) have opened up new
possibilities for versatile and efficient visual perception. In this work, we introduce Seal, a …
possibilities for versatile and efficient visual perception. In this work, we introduce Seal, a …
On the benefits of 3d pose and tracking for human action recognition
J Rajasegaran, G Pavlakos… - Proceedings of the …, 2023 - openaccess.thecvf.com
In this work we study the benefits of using tracking and 3D poses for action recognition. To
achieve this, we take the Lagrangian view on analysing actions over a trajectory of human …
achieve this, we take the Lagrangian view on analysing actions over a trajectory of human …
A survey on masked autoencoder for self-supervised learning in vision and beyond
Masked autoencoders are scalable vision learners, as the title of MAE\cite {he2022masked},
which suggests that self-supervised learning (SSL) in vision might undertake a similar …
which suggests that self-supervised learning (SSL) in vision might undertake a similar …