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 …
Adapt or perish: Adaptive sparse transformer with attentive feature refinement for image restoration
Transformer-based approaches have achieved promising performance in image restoration
tasks given their ability to model long-range dependencies which is crucial for recovering …
tasks given their ability to model long-range dependencies which is crucial for recovering …
Extdm: Distribution extrapolation diffusion model for video prediction
Video prediction is a challenging task due to its nature of uncertainty especially for
forecasting a long period. To model the temporal dynamics advanced methods benefit from …
forecasting a long period. To model the temporal dynamics advanced methods benefit from …
Alignsam: Aligning segment anything model to open context via reinforcement learning
Powered by massive curated training data Segment Anything Model (SAM) has
demonstrated its impressive generalization capabilities in open-world scenarios with the …
demonstrated its impressive generalization capabilities in open-world scenarios with the …
Lake-red: Camouflaged images generation by latent background knowledge retrieval-augmented diffusion
Camouflaged vision perception is an important vision task with numerous practical
applications. Due to the expensive collection and labeling costs this community struggles …
applications. Due to the expensive collection and labeling costs this community struggles …
Ordinal label distribution learning
C Wen, X Zhang, X Yao, J Yang - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Label distribution learning (LDL) is a recent hot topic, in which ambiguity is modeled via
description degrees of the labels. However, in common LDL tasks, eg, age estimation, labels …
description degrees of the labels. However, in common LDL tasks, eg, age estimation, labels …
Timeline and Boundary Guided Diffusion Network for Video Shadow Detection
Video Shadow Detection (VSD) aims to detect the shadow masks with frame sequence.
Existing works suffer from inefficient temporal learning. Moreover, few works address the …
Existing works suffer from inefficient temporal learning. Moreover, few works address the …
PlaneAC: Line-guided planar 3D reconstruction based on self-attention and convolution hybrid model
J Zhang, J Yang, F Fu, J Ma - Pattern Recognition, 2024 - Elsevier
Planar 3D reconstruction aims to simultaneously extract plane instances and reconstruct the
local 3D model through the estimated plane parameters. Existing methods achieve …
local 3D model through the estimated plane parameters. Existing methods achieve …
Ist-net: Prior-free category-level pose estimation with implicit space transformation
Category-level 6D pose estimation aims to predict the poses and sizes of unseen objects
from a specific category. Thanks to prior deformation, which explicitly adapts a category …
from a specific category. Thanks to prior deformation, which explicitly adapts a category …
Annotation-efficient polyp segmentation via active learning
Deep learning-based techniques have proven effective in polyp segmentation tasks when
provided with sufficient pixel-wise labeled data. However, the high cost of manual …
provided with sufficient pixel-wise labeled data. However, the high cost of manual …