Related papers: Anchor-Constrained Viterbi for Set-Supervised Acti…

We present our novel deep multi-task learning method for medical image segmentation. Existing multi-task methods demand ground truth annotations for both the primary and auxiliary tasks. Contrary to it, we propose to generate the…

When we say a person is texting, can you tell the person is walking or sitting? Emphatically, no. In order to solve this incomplete representation problem, this paper presents a sub-action descriptor for detailed action detection. The…

Weakly supervised instance segmentation reduces the cost of annotations required to train models. However, existing approaches which rely only on image-level class labels predominantly suffer from errors due to (a) partial segmentation of…

We propose a soft attention based model for the task of action recognition in videos. We use multi-layered Recurrent Neural Networks (RNNs) with Long Short-Term Memory (LSTM) units which are deep both spatially and temporally. Our model…

Semi-Supervised Visual Grounding (SSVG) is a new challenge for its sparse labeled data with the need for multimodel understanding. A previous study, RefTeacher, makes the first attempt to tackle this task by adopting the teacher-student…

A large amount of manual segmentation is typically required to train a robust segmentation network so that it can segment objects of interest in a new imaging modality. The manual efforts can be alleviated if the manual segmentation in one…

We present a method for weakly-supervised action localization based on graph convolutions. In order to find and classify video time segments that correspond to relevant action classes, a system must be able to both identify discriminative…

In this paper, we introduce the on-line Viterbi algorithm for decoding hidden Markov models (HMMs) in much smaller than linear space. Our analysis on two-state HMMs suggests that the expected maximum memory used to decode sequence of length…

Joint segmentation and classification of fine-grained actions is important for applications of human-robot interaction, video surveillance, and human skill evaluation. However, despite substantial recent progress in large-scale action…

We present a semi-supervised learning algorithm for learning discrete factor analysis models with arbitrary structure on the latent variables. Our algorithm assumes that every latent variable has an "anchor", an observed variable with only…

Few-shot semantic segmentation addresses the learning task in which only few images with ground truth pixel-level labels are available for the novel classes of interest. One is typically required to collect a large mount of data (i.e., base…

Weakly-supervised object detection has recently attracted increasing attention since it only requires image-levelannotations. However, the performance obtained by existingmethods is still far from being satisfactory compared with…

Understanding the structure of complex activities in untrimmed videos is a challenging task in the area of action recognition. One problem here is that this task usually requires a large amount of hand-annotated minute- or even hour-long…

Neural networks are a powerful framework for foreground segmentation in video acquired by static cameras, segmenting moving objects from the background in a robust way in various challenging scenarios. The premier methods are those based on…

Action segmentation as a milestone towards building automatic systems to understand untrimmed videos has received considerable attention in the recent years. It is typically being modeled as a sequence labeling problem but contains…

In this work, we focus on semi-supervised learning for video action detection. Video action detection requires spatiotemporal localization in addition to classification, and a limited amount of labels makes the model prone to unreliable…

In this paper, we address a novel task, namely weakly-supervised spatio-temporally grounding natural sentence in video. Specifically, given a natural sentence and a video, we localize a spatio-temporal tube in the video that semantically…

The task of temporally grounding textual queries in videos is to localize one video segment that semantically corresponds to the given query. Most of the existing approaches rely on segment-sentence pairs (temporal annotations) for…

We present a model for temporally precise action spotting in videos, which uses a dense set of detection anchors, predicting a detection confidence and corresponding fine-grained temporal displacement for each anchor. We experiment with two…

Temporal action segmentation (TAS) divides untrimmed videos into labeled action segments. While fully supervised methods have advanced the field, challenges such as action variability, ambiguous boundaries, and high annotation costs remain,…