Related papers: Featureless: Bypassing feature extraction in actio…

Most action recognition solutions rely on dense sampling to precisely cover the informative temporal clip. Extensively searching temporal region is expensive for a real-world application. In this work, we focus on improving the inference…

This paper introduces a novel approach to active feature acquisition for classification, which is the task of sequentially selecting the most informative subset of features to achieve optimal prediction performance during testing while…

Brain-inspired deep predictive coding networks (DPCNs) effectively model and capture video features through a bi-directional information flow, even without labels. They are based on an overcomplete description of video scenes, and one of…

Feature selection is essential for effective visual recognition. We propose an efficient joint classifier learning and feature selection method that discovers sparse, compact representations of input features from a vast sea of candidates,…

Not all video frames are equally informative for recognizing an action. It is computationally infeasible to train deep networks on all video frames when actions develop over hundreds of frames. A common heuristic is uniformly sampling a…

Standard methods for video recognition use large CNNs designed to capture spatio-temporal data. However, training these models requires a large amount of labeled training data, containing a wide variety of actions, scenes, settings and…

Despite huge success in the image domain, modern detection models such as Faster R-CNN have not been used nearly as much for video analysis. This is arguably due to the fact that detection models are designed to operate on single frames and…

In this paper, we leverage existing statistical methods to better understand feature learning from data. We tackle this by modifying the model-free variable selection method, Feature Ordering by Conditional Independence (FOCI), which is…

We present a generative framework for zero-shot action recognition where some of the possible action classes do not occur in the training data. Our approach is based on modeling each action class using a probability distribution whose…

Although dense local spatial-temporal features with bag-of-features representation achieve state-of-the-art performance for action recognition, the huge feature number and feature size prevent current methods from scaling up to real size…

Zero-shot action recognition, which recognizes actions in videos without having received any training examples, is gaining wide attention considering it can save labor costs and training time. Nevertheless, the performance of zero-shot…

In this paper, we propose a novel fully unsupervised framework that learns action representations suitable for the action segmentation task from the single input video itself, without requiring any training data. Our method is a deep metric…

Unsupervised video class incremental learning (uVCIL) represents an important learning paradigm for learning video information without forgetting, and without considering any data labels. Prior approaches have focused on supervised…

In the face of the video data deluge, today's expensive clip-level classifiers are increasingly impractical. We propose a framework for efficient action recognition in untrimmed video that uses audio as a preview mechanism to eliminate both…

Recent unsupervised pre-training methods have shown to be effective on language and vision domains by learning useful representations for multiple downstream tasks. In this paper, we investigate if such unsupervised pre-training methods can…

The task of temporally detecting and segmenting actions in untrimmed videos has seen an increased attention recently. One problem in this context arises from the need to define and label action boundaries to create annotations for training…

Action recognition is a fundamental ability for social species. Yet, its underlying computations are not well understood. Classical psychophysical studies using simplified stimuli have shown that humans can perceive body motion even under…

This paper introduces a novel method for self-supervised video representation learning via feature prediction. In contrast to the previous methods that focus on future feature prediction, we argue that a supervisory signal arising from…

Action recognition in videos has attracted a lot of attention in the past decade. In order to learn robust models, previous methods usually assume videos are trimmed as short sequences and require ground-truth annotations of each video…

Current approaches for activity recognition often ignore constraints on computational resources: 1) they rely on extensive feature computation to obtain rich descriptors on all frames, and 2) they assume batch-mode access to the entire test…