Large-Scale Video Classification with Convolutional Neural Networks

By Andrej Karpathy, George Toderici, Sanketh Shetty, Thomas K. Leung, Rahul Sukthankar, Li Fei-Fei. 2014

6,709 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Rethinking the Inception Architecture for Computer Vision (2015, methodology): “Since the 2012 ImageNet competition [16] winning entry by Krizhevsky et al [9], their network “AlexNet” has been successfully applied to a larger variety of computer vision tasks, for example to object-detection [5], segmentation [12], human pose estimation [22], video classification [8], object tra”
Learning Video Representations from Textual Web Supervision (2020, methodology): “Other approaches use user-deﬁned keywords or tags [20, 28, 43, 19] or algorithmically-generated topics [1, 31] to the same end.”
End-to-End Learning of Visual Representations From Uncurated Instructional Videos (2019, background): “Notably, the largest action datasets today are still orders of magnitude smaller (UCF101 [36], ActivityNet [7]) compared to large image datasets, they often contain label noise and target specific domains such as sports (Sports1M [20]).”
TensorFlow: A system for large-scale machine learning (2016, neutral): “In recent years, machine learning has driven advances in many different ﬁelds [3, 5, 23, 24, 30, 27, 40, 45, 48, 50, 55, 68, 69, 73, 76].”
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning (2016, background): “r network “AlexNet” has been successfully applied to a larger variety of computer vision tasks, for example to object-detection [4], segmentation [10], human pose estimation [17], video classiﬁcation [7], object tracking [18], and superresolution [3]. These examples are but a few of all the applicat”
Learning Energy-Based Spatial-Temporal Generative ConvNets for Dynamic Patterns (2019, background): “section, we provide a comprehensive review of related work. Dynamic pattern recognition. Recognizing dynamic patterns (e.g., actions) with ConvNets has been extensively studied in the past few years. [4] applied ConvNets with deep structures on a largescale video dataset for classiﬁcation. [5] desig”
Perceiver: General Perception with Iterative Attention (2021, background): “But if we move to a stereo pair, we must decide how to modify this structure to jointly process the pixels from both sensors: should we use an early or late fusion architecture (Karpathy et al., 2014) or should we sum or concatenate features?”
TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems (2016, neutral): “We and others at Google have performed a wide variety of research using DistBelief including work on unsupervised learning [31], language representation [35, 52], models for image classification and object detection [16, 48], video classification [27], speech recognition [56, 21, 20],”
Deep multi-scale video prediction beyond mean square error (2015, methodology): “We use the Sports1m for the training, because most of UCF101 frames only have a very small portion of the image actually moving, while the rest is just a ﬁxed background.”
Multiview Transformers for Video Recognition (2022, background): “At the same time, CNNs and RNNs have quickly become the de-facto backbones for video understanding tasks [32, 50, 57].”
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset (2017, background): “Deep Networks [15], Sports 1M pre-training 65.”
Two-Stream Convolutional Networks for Action Recognition in Videos (2014, methodology): “Interestingly, [14] found that a network, operating on individual video frames, performs similarly to the networks, whose input is a stack of frames.”
The Kinetics Human Action Video Dataset (2017, background): “This can be achieved by using them to extract features independently from each frame then pooling their predictions across the whole video [14].”
Action-Conditional Video Prediction using Deep Networks in Atari Games (2015, background): “This encoding can be viewed as early-fusion [14] (other types of fusions, e.”
Dense-Captioning Events in Videos (2017, background): “ start and end time. Finally, we report performances of our model for dense-captioning events, video retrieval and localization. 1. Introduction With the introduction of large scale activity datasets [26, 21, 15, 4], it has become possible to categorize videos into a discrete set of action categorie”
Visual7W: Grounded Question Answering in Images (2015, background): “The recent development of deep learning technologies has achieved successes in many perceptual visual tasks such as object recognition, image classiﬁcation and pose estimation [15, 21, 25, 38, 39, 42, 43].”