Related papers: A novel learning-based frame pooling method for Ev…
Recognizing target objects using an event-based camera draws more and more attention in recent years. Existing works usually represent the event streams into point-cloud, voxel, image, etc, and learn the feature representations using…
In this work, we present novel temporal encoding methods for action and activity classification by extending the unsupervised rank pooling temporal encoding method in two ways. First, we present "discriminative rank pooling" in which the…
We present a scalable framework designed to craft efficient lightweight models for video object detection utilizing self-training and knowledge distillation techniques. We scrutinize methodologies for the ideal selection of training images…
We propose a light-weight video frame interpolation algorithm. Our key innovation is an instance-level supervision that allows information to be learned from the high-resolution version of similar objects. Our experiment shows that the…
3D shape analysis is an important research topic in computer vision and graphics. While existing methods have generalized image-based deep learning to meshes using graph-based convolutions, the lack of an effective pooling operation…
Video-based human pose estimation in crowded scenes is a challenging problem due to occlusion, motion blur, scale variation and viewpoint change, etc. Prior approaches always fail to deal with this problem because of (1) lacking of usage of…
Existing image-based rendering methods usually adopt depth-based image warping operation to synthesize novel views. In this paper, we reason the essential limitations of the traditional warping operation to be the limited neighborhood and…
We present a Multi-Scale Pyramidal Pooling Network, featuring a novel pyramidal pooling layer at multiple scales and a novel encoding layer. Thanks to the former the network does not require all images of a given classification task to be…
The objective of this work is human pose estimation in videos, where multiple frames are available. We investigate a ConvNet architecture that is able to benefit from temporal context by combining information across the multiple frames…
The feature frame is a key idea of feature matching problem between two images. However, most of the traditional matching methods only simply employ the spatial location information (the coordinates), which ignores the shape and orientation…
A new unified video analytics framework (ER3) is proposed for complex event retrieval, recognition and recounting, based on the proposed video imprint representation, which exploits temporal correlations among image features across video…
Recent co-part segmentation methods mostly operate in a supervised learning setting, which requires a large amount of annotated data for training. To overcome this limitation, we propose a self-supervised deep learning method for co-part…
This paper presents a novel method for rare event detection from an image pair with class-imbalanced datasets. A straightforward approach for event detection tasks is to train a detection network from a large-scale dataset in an end-to-end…
High accuracy video label prediction (classification) models are attributed to large scale data. These data could be frame feature sequences extracted by a pre-trained convolutional-neural-network, which promote the efficiency for creating…
We conduct an in-depth exploration of different strategies for doing event detection in videos using convolutional neural networks (CNNs) trained for image classification. We study different ways of performing spatial and temporal pooling,…
We propose smoothed max pooling loss and its application to keyword spotting systems. The proposed approach jointly trains an encoder (to detect keyword parts) and a decoder (to detect whole keyword) in a semi-supervised manner. The…
The increasing global crime rate, coupled with substantial human and property losses, highlights the limitations of traditional surveillance methods in promptly detecting diverse and unexpected acts of violence. Addressing this pressing…
Automatic face recognition has received significant performance improvement by developing specialised facial image representations. On the other hand, generic object recognition has rarely been applied to the face recognition. Spatial…
Event detection in unconstrained videos is conceived as a content-based video retrieval with two modalities: textual and visual. Given a text describing a novel event, the goal is to rank related videos accordingly. This task is…
Video object detection is more challenging compared to image object detection. Previous works proved that applying object detector frame by frame is not only slow but also inaccurate. Visual clues get weakened by defocus and motion blur,…