Search Results for author:
Found 28 papers, 12 papers with code
On Diverse Asynchronous Activity Anticipation
We investigate the joint anticipation of long-term activity labels and their corresponding times with the aim of improving both the naturalness and diversity of predictions.
Visual Concept Connectome (VCC): Open World Concept Discovery and their Interlayer Connections in Deep Models
Understanding what deep network models capture in their learned representations is a fundamental challenge in computer vision.
Selective, Interpretable, and Motion Consistent Privacy Attribute Obfuscation for Action Recognition
Global obfuscation hides privacy sensitive regions, but also contextual regions important for action recognition.
Understanding Video Transformers for Segmentation: A Survey of Application and Interpretability
In this survey, we address the above with a thorough discussion of various categories of video segmentation, a component-wise discussion of the state-of-the-art transformer-based models, and a review of related interpretability methods.
StepFormer: Self-supervised Step Discovery and Localization in Instructional Videos
This motivates the need to temporally localize the instruction steps in such videos, i. e. the task called key-step localization.
A Unified Multiscale Encoder-Decoder Transformer for Video Segmentation
In this paper, we present an end-to-end trainable unified multiscale encoder-decoder transformer that is focused on dense prediction tasks in video.
Quantifying and Learning Static vs. Dynamic Information in Deep Spatiotemporal Networks
(ii) Some datasets that are assumed to be biased toward dynamics are actually biased toward static information.
Sports Video Analysis on Large-Scale Data
In this paper, we propose a novel large-scale NBA dataset for Sports Video Analysis (NSVA) with a focus on captioning, to address the above challenges.
Is Appearance Free Action Recognition Possible?
Presently, a methodology and corresponding dataset to isolate the effects of dynamic information in video are missing.
A Deeper Dive Into What Deep Spatiotemporal Networks Encode: Quantifying Static vs. Dynamic Information
To show the efficacy of our approach, we analyse two widely studied tasks, action recognition and video object segmentation.
P3IV: Probabilistic Procedure Planning from Instructional Videos with Weak Supervision
Our model is based on a transformer equipped with a memory module, which maps the start and goal observations to a sequence of plausible actions.
Temporal Transductive Inference for Few-Shot Video Object Segmentation
In this paper, we present a simple but effective temporal transductive inference (TTI) approach that leverages temporal consistency in the unlabelled video frames during few-shot inference.
Interpretable Deep Feature Propagation for Early Action Recognition
Early action recognition (action prediction) from limited preliminary observations plays a critical role for streaming vision systems that demand real-time inference, as video actions often possess elongated temporal spans which cause undesired latency.
Review of Video Predictive Understanding: Early Action Recognition and Future Action Prediction
Action prediction is a major sub-area of video predictive understanding and is the focus of this review.
Detecting Biological Locomotion in Video: A Computational Approach
An algorithm is developed to measure the presence of these traits in tracked objects to determine if they correspond to a biological entity in locomotion.
Where Are You Heading? Dynamic Trajectory Prediction With Expert Goal Examples
Goal-conditioned approaches recently have been found very useful to human trajectory prediction, when adequate goal estimates are provided.
Ranked #5 on
Trajectory Prediction
on ETH
Why Convolutional Networks Learn Oriented Bandpass Filters: Theory and Empirical Support
A standard explanation of this result is that these filters reflect the structure of the images that they have been exposed to during training: Natural images typically are locally composed of oriented contours at various scales and oriented bandpass filters are matched to such structure.
Why Convolutional Networks Learn Oriented Bandpass Filters: A Hypothesis
A standard explanation of this result is that these filters reflect the structure of the images that they have been exposed to during training: Natural images typically are locally composed of oriented contours at various scales and oriented bandpass filters are matched to such structure.
A New Large Scale Dynamic Texture Dataset with Application to ConvNet Understanding
This paper introduces a new large scale dynamic texture dataset.
What Do We Understand About Convolutional Networks?
This document will review the most prominent proposals using multilayer convolutional architectures.
What have we learned from deep representations for action recognition?
In this paper, we shed light on deep spatiotemporal representations by visualizing what two-stream models have learned in order to recognize actions in video.
A Spatiotemporal Oriented Energy Network for Dynamic Texture Recognition
Another key aspect of the network is its recurrent nature, whereby the output of each layer of processing feeds back to the input.
Spatiotemporal Multiplier Networks for Video Action Recognition
This paper presents a general ConvNet architecture for video action recognition based on multiplicative interactions of spacetime features.
Ranked #47 on
Action Recognition
on HMDB-51
Temporal Residual Networks for Dynamic Scene Recognition
Finally, our temporal ResNet boosts recognition performance and establishes a new state-of-the-art on dynamic scene recognition, as well as on the complementary task of action recognition.
Spatiotemporal Residual Networks for Video Action Recognition
Two-stream Convolutional Networks (ConvNets) have shown strong performance for human action recognition in videos.
Ranked #48 on
Action Recognition
on UCF101
Review of Action Recognition and Detection Methods
In this report, a thorough review of various action recognition and detection algorithms in computer vision is provided by analyzing the two-step process of a typical action recognition and detection algorithm: (i) extraction and encoding of features, and (ii) classifying features into action classes.
Dynamically Encoded Actions Based on Spacetime Saliency
By using the resulting definition of saliency during feature pooling we show that action recognition performance achieves state-of-the-art levels on three widely considered action recognition datasets.
Bags of Spacetime Energies for Dynamic Scene Recognition
This paper presents a unified bag of visual word (BoW) framework for dynamic scene recognition.
