Action Recognition

Benchmarks

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Latest papers without code

The 3TConv: An Intrinsic Approach to Explainable 3D CNNs

ICLR 2021

In a 3TConv the 3D convolutional filter is obtained by learning a 2D filter and a set of temporal transformation parameters, resulting in a sparse filter requiring less parameters.

ACTION RECOGNITION

Negative Data Augmentation

ICLR 2021

Empirically, models trained with our method achieve improved conditional/unconditional image generation along with improved anomaly detection capabilities.

ACTION RECOGNITION ANOMALY DETECTION CONTRASTIVE LEARNING DATA AUGMENTATION IMAGE CLASSIFICATION IMAGE GENERATION OBJECT DETECTION REPRESENTATION LEARNING

Learning Self-Similarity in Space and Time as a Generalized Motion for Action Recognition

ICLR 2021

We leverage the whole volume of STSS and let our model learn to extract an effective motion representation from it.

ACTION RECOGNITION VIDEO UNDERSTANDING

A Unified Framework to Analyze and Design the Nonlocal Blocks for Neural Networks

ICLR 2021

When choosing Chebyshev graph filter, a generalized formulation can be derived for explaining the existing nonlocal-based blocks (e. g. nonlocal block, nonlocal stage, double attention block) and uses to analyze their irrationality.

ACTION RECOGNITION FINE-GRAINED IMAGE CLASSIFICATION

Beyond the Pixels: Exploring the Effects of Bit-Level Network and File Corruptions on Video Model Robustness

ICLR 2021

We investigate the robustness of video machine learning models to bit-level network and file corruptions, which can arise from network transmission failures or hardware errors, and explore defenses against such corruptions.

ACTION RECOGNITION MULTI-OBJECT TRACKING

Temporal Difference Networks for Action Recognition

ICLR 2021

To mitigate this issue, this paper presents a new video architecture, termed as Temporal Difference Network (TDN), with a focus on capturing multi-scale temporal information for efficient action recognition.

ACTION RECOGNITION ACTION RECOGNITION IN VIDEOS ACTION RECOGNITION IN VIDEOS

Exploring Sub-Pseudo Labels for Learning from Weakly-Labeled Web Videos

ICLR 2021

To address this issue, we introduce a new method for pre-training video action recognition models using queried web videos.

ACTION RECOGNITION

Learning Visual Representation from Human Interactions

ICLR 2021

Learning effective representations of visual data that generalize to a variety of downstream tasks has been a long quest for computer vision.

ACTION RECOGNITION DEPTH ESTIMATION REPRESENTATION LEARNING SCENE CLASSIFICATION

PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences

ICLR 2021

Then, a spatial convolution is employed to capture the local structure of points in the 3D space, and a temporal convolution is used to model the dynamics of the spatial regions along the time dimension.

3D ACTION RECOGNITION SEMANTIC SEGMENTATION

AdaFuse: Adaptive Temporal Fusion Network for Efficient Action Recognition

ICLR 2021

Specifically, the necessary information from the historical convolution feature maps is fused with current pruned feature maps with the goal of improving both recognition accuracy and efficiency.

ACTION RECOGNITION