Papers with Code 아카이브

Video Classification

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

하위 태스크: 2
평가표: 12
보존된 평가 기록: 31

Video Classification is the task of producing a label that is relevant to the video given its frames. A good video level classifier is one that not only provides accurate frame labels, but also best describes the entire video given the features and the annotations of the various frames in the video. For example, a video might contain a tree in some frame, but the label that is central to the video might be something else (e.g., “hiking”). The granularity of the labels that are needed to describe the frames and the video depends on the task. Typical tasks include assigning one or more global labels to the video, and assigning one or more labels for each frame inside the video.

Source: Efficient Large Scale Video Classification

논문

이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.

Video Classification

논문

On the Post-hoc Explainability of Deep Echo State Networks for Time Series Forecasting, Image and Video Classification

Distribution Adaptive INT8 Quantization for Training CNNs

Is Space-Time Attention All You Need for Video Understanding?

RANP: Resource Aware Neuron Pruning at Initialization for 3D CNNs

Privacy-Preserving Video Classification with Convolutional Neural Networks

Emotional EEG Classification using Connectivity Features and Convolutional Neural Networks

Piano Skills Assessment

Self-Supervised Pretraining of 3D Features on any Point-Cloud

Reinforcement Learning with Latent Flow

CNNs for JPEGs: A Study in Computational Cost

Temporal Bilinear Encoding Network of Audio-Visual Features at Low Sampling Rates

Smoothed Gaussian Mixture Models for Video Classification and Recommendation

VideoMix: Rethinking Data Augmentation for Video Classification

Wisdom of Committees: An Overlooked Approach To Faster and More Accurate Models

Diverse Temporal Aggregation and Depthwise Spatiotemporal Factorization for Efficient Video Classification

t-EVA: Time-Efficient t-SNE Video Annotation

Deep Multimodality Learning for UAV Video Aesthetic Quality Assessment

RANP: Resource Aware Neuron Pruning at Initialization for 3D CNNs

Attention-Aware Noisy Label Learning for Image Classification

Discovering Dynamic Salient Regions for Spatio-Temporal Graph Neural Networks

Multi-Label Activity Recognition using Activity-specific Features and Activity Correlations

Defending Against Multiple and Unforeseen Adversarial Videos

Active Contrastive Learning of Audio-Visual Video Representations

Making a Case for 3D Convolutions for Object Segmentation in Videos

Recurrent Deconvolutional Generative Adversarial Networks with Application to Text Guided Video Generation

Actor-Action Video Classification CSC 249/449 Spring 2020 Challenge Report

Approximated Bilinear Modules for Temporal Modeling

AttentionNAS: Spatiotemporal Attention Cell Search for Video Classification

Uncertainty-Aware Weakly Supervised Action Detection from Untrimmed Videos

MotionSqueeze: Neural Motion Feature Learning for Video Understanding

Region-based Non-local Operation for Video Classification

3D CNN-PCA: A Deep-Learning-Based Parameterization for Complex Geomodels

Generalized Few-Shot Video Classification with Video Retrieval and Feature Generation

SmallBigNet: Integrating Core and Contextual Views for Video Classification

Pyramidal Convolution: Rethinking Convolutional Neural Networks for Visual Recognition

Learn to cycle: Time-consistent feature discovery for action recognition