paper-with-me

Papers

Temporal Contrastive Learning with Curriculum

2022-09-02 · Shuvendu Roy, Ali Etemad

We present ConCur, a contrastive video representation learning method that uses curriculum learning to impose a dynamic sampling strategy in contrastive training. More specifically, ConCur starts the contrastive training with easy positive samples (temporally close and semantically similar clips), and as the training progresses, it increases the temporal span effectively sampling hard positives (temporally away and semantically dissimilar). To learn better context-aware representations, we also propose an auxiliary task of predicting the temporal distance between a positive pair of clips. We conduct extensive experiments on two popular action recognition datasets, UCF101 and HMDB51, on which our proposed method achieves state-of-the-art performance on two benchmark tasks of video action recognition and video retrieval. We explore the impact of encoder backbones and pre-training strategies by using R(2+1)D and C3D encoders and pre-training on Kinetics-400 and Kinetics-200 datasets. Moreover, a detailed ablation study shows the effectiveness of each of the components of our proposed method.

📄 PDF Abstract BibTeX arXiv:2209.00760

Code (0)

등록된 구현이 없습니다.

Tasks

Action RecognitionContrastive LearningRepresentation LearningRetrievalTemporal Action LocalizationVideo Retrieval

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Batch Normalization 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
(2+1)D Convolution A (2+1)D Convolution is a type of convolution used for action recognition convolutional neural networks, with a spatiotemporal…
Average Pooling 설명 없음
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Residual Connection 설명 없음
R(2+1)D A R(2+1)D convolutional neural network is a network for action recognition that employs R(2+1)D convolutions in a…

Similar Papers 제목 키워드 기반

Weakly-supervised Temporal Path Representation Learning with Contrastive Curriculum Learning -- Extended Version

2022-03-30 · Sean Bin Yang, Chenjuan Guo, Jilin Hu, Bin Yang 외

In step with the digitalization of transportation, we are witnessing a growing range of path-based smart-city applications, e.g., travel-time estimation and travel path ranking. A temporal path(TP) that includes temporal…

Contrastive LearningRepresentation LearningTravel Time Estimation

CCML: Curriculum and Contrastive Learning Enhanced Meta-Learner for Personalized Spatial Trajectory Prediction

2024-03-01 · journal 2024 3 · Jing Zhao, Jiajie Xu, Yuan Xu, Junhua Fang 외

Spatial trajectory prediction is a fundamental problem for diverse location-based applications. However, existing methods fall short in learning and generalization, and cannot sufficiently capture users’ spatiotemporal p…

Contrastive LearningMeta-LearningTrajectory Prediction

ConCur: Self-supervised graph representation based on contrastive learning with curriculum negative sampling

2023-09-01 · journal 2023 9 · Rong Yan, Peng Bao

Contrastive learning has made breakthrough advancements in graph representation learning, which encourages the representation of positive samples to be close and those of negative samples to be far away. However, existin…

Contrastive LearningGraph Representation LearningNode ClassificationRepresentation Learning+1

Efficient Contrastive Learning via Novel Data Augmentation and Curriculum Learning

2021-09-10 · EMNLP 2021 11 · Seonghyeon Ye, Jiseon Kim, Alice Oh

We introduce EfficientCL, a memory-efficient continual pretraining method that applies contrastive learning with novel data augmentation and curriculum learning. For data augmentation, we stack two types of operation seq…

Continual PretrainingContrastive LearningData AugmentationSentence

ACDC: Adaptive Curriculum Planning with Dynamic Contrastive Control for Goal-Conditioned Reinforcement Learning in Robotic Manipulation

2026-03-02 · Xuerui Wang, Guangyu Ren, Tianhong Dai, Bintao Hu 외 arxiv

Goal-conditioned reinforcement learning has shown considerable potential in robotic manipulation; however, existing approaches remain limited by their reliance on prioritizing collected experience, resulting in suboptima…

Reinforcement LearningContrastive Learning