Search Results for author:
Found 18 papers, 14 papers with code
About Time: Advances, Challenges, and Outlooks of Action Understanding
This survey comprehensively reviews advances in uni- and multi-modal action understanding across a range of tasks.
LAVIB: A Large-scale Video Interpolation Benchmark
This paper introduces a LArge-scale Video Interpolation Benchmark (LAVIB) for the low-level video task of Video Frame Interpolation (VFI).
Ranked #1 on
Video Frame Interpolation
on LAVIB
Every Shot Counts: Using Exemplars for Repetition Counting in Videos
We propose an exemplar-based approach that discovers visual correspondence of video exemplars across repetitions within target videos.
Ranked #1 on
Repetitive Action Counting
on UCFRep
Holistic Representation Learning for Multitask Trajectory Anomaly Detection
We encode temporally occluded trajectories, jointly learn latent representations of the occluded segments, and reconstruct trajectories based on expected motions across different temporal segments.
Ranked #1 on
Video Anomaly Detection
on HR-Avenue
Leaping Into Memories: Space-Time Deep Feature Synthesis
The success of deep learning models has led to their adaptation and adoption by prominent video understanding methods.
Play It Back: Iterative Attention for Audio Recognition
A key function of auditory cognition is the association of characteristic sounds with their corresponding semantics over time.
Ranked #4 on
Audio Classification
on EPIC-KITCHENS-100
The Wisdom of Crowds: Temporal Progressive Attention for Early Action Prediction
We propose a bottleneck-based attention model that captures the evolution of the action, through progressive sampling over fine-to-coarse scales.
Ranked #1 on
Early Action Prediction
on UCF101
AdaPool: Exponential Adaptive Pooling for Information-Retaining Downsampling
We evaluate adaUnPool on image and video super-resolution and frame interpolation.
Efficient Modelling Across Time of Human Actions and Interactions
The hierarchical extraction of features models variations of relatively similar classes the same as very dissimilar classes.
The Mind's Eye: Visualizing Class-Agnostic Features of CNNs
Visual interpretability of Convolutional Neural Networks (CNNs) has gained significant popularity because of the great challenges that CNN complexity imposes to understanding their inner workings.
Refining activation downsampling with SoftPool
Convolutional Neural Networks (CNNs) use pooling to decrease the size of activation maps.
Multi-Temporal Convolutions for Human Action Recognition in Videos
To address this challenge, we present a novel spatio-temporal convolution block that is capable of extracting spatio-temporal patterns at multiple temporal resolutions.
Action Recognition In Videos
Temporal Action Localization
+1
Learn to cycle: Time-consistent feature discovery for action recognition
Generalizing over temporal variations is a prerequisite for effective action recognition in videos.
Ranked #3 on
Action Recognition
on HACS
Learning Class Regularized Features for Action Recognition
We show that using Class Regularization blocks in state-of-the-art CNN architectures for action recognition leads to systematic improvement gains of 1. 8%, 1. 2% and 1. 4% on the Kinetics, UCF-101 and HMDB-51 datasets, respectively.
Spatio-Temporal FAST 3D Convolutions for Human Action Recognition
Motivated by the often distinctive temporal characteristics of actions in either horizontal or vertical direction, we introduce a novel convolution block for CNN architectures with video input.
Class Feature Pyramids for Video Explanation
We demonstrate the method on six state-of-the-art 3D convolution neural networks (CNNs) on three action recognition (Kinetics-400, UCF-101, and HMDB-51) and two egocentric action recognition datasets (EPIC-Kitchens and EGTEA Gaze+).
Saliency Tubes: Visual Explanations for Spatio-Temporal Convolutions
Deep learning approaches have been established as the main methodology for video classification and recognition.
Analyzing Human-Human Interactions: A Survey
The main challenges stem from dealing with the considerable variation in recording setting, the appearance of the people depicted and the coordinated performance of their interaction.
