Unsupervised point cloud representation learning with deep neural networks: A survey
Point cloud data have been widely explored due to its superior accuracy and robustness
under various adverse situations. Meanwhile, deep neural networks (DNNs) have achieved …
under various adverse situations. Meanwhile, deep neural networks (DNNs) have achieved …
Towards global video scene segmentation with context-aware transformer
Videos such as movies or TV episodes usually need to divide the long storyline into
cohesive units, ie, scenes, to facilitate the understanding of video semantics. The key …
cohesive units, ie, scenes, to facilitate the understanding of video semantics. The key …
Meltr: Meta loss transformer for learning to fine-tune video foundation models
Foundation models have shown outstanding performance and generalization capabilities
across domains. Since most studies on foundation models mainly focus on the pretraining …
across domains. Since most studies on foundation models mainly focus on the pretraining …
Frame-wise action representations for long videos via sequence contrastive learning
Prior works on action representation learning mainly focus on designing various
architectures to extract the global representations for short video clips. In contrast, many …
architectures to extract the global representations for short video clips. In contrast, many …
Static and dynamic concepts for self-supervised video representation learning
In this paper, we propose a novel learning scheme for self-supervised video representation
learning. Motivated by how humans understand videos, we propose to first learn general …
learning. Motivated by how humans understand videos, we propose to first learn general …
A electricity theft detection method through contrastive learning in smart grid
As an important edge device of power grid, smart meters enable the detection of illegal
behaviors such as electricity theft by analyzing large-scale electricity consumption data …
behaviors such as electricity theft by analyzing large-scale electricity consumption data …
Scene consistency representation learning for video scene segmentation
A long-term video, such as a movie or TV show, is composed of various scenes, each of
which represents a series of shots sharing the same semantic story. Spotting the correct …
which represents a series of shots sharing the same semantic story. Spotting the correct …
Alignment-uniformity aware representation learning for zero-shot video classification
Most methods tackle zero-shot video classification by aligning visual-semantic
representations within seen classes, which limits generalization to unseen classes. To …
representations within seen classes, which limits generalization to unseen classes. To …
Dual contrastive learning for spatio-temporal representation
Contrastive learning has shown promising potential in self-supervised spatio-temporal
representation learning. Most works naively sample different clips to construct positive and …
representation learning. Most works naively sample different clips to construct positive and …
Temporal augmented contrastive learning for micro-expression recognition
T Wang, L Shang - Pattern Recognition Letters, 2023 - Elsevier
Micro-expressions (MEs) can reveal the hidden but real emotion and are usually caused
spontaneously. However, the characteristics of subtlety and temporariness with the lack of …
spontaneously. However, the characteristics of subtlety and temporariness with the lack of …