Related papers: Unified Fully and Timestamp Supervised Temporal Ac…
In this paper, we introduce a new sequence-to-sequence learning framework for RGB-based and multi-modal object tracking. First, we present SeqTrack for RGB-based tracking. It casts visual tracking as a sequence generation task, forecasting…
Animals have evolved highly functional visual systems to understand motion, assisting perception even under complex environments. In this paper, we work towards developing a computer vision system able to segment objects by exploiting…
Video action segmentation have been widely applied in many fields. Most previous studies employed video-based vision models for this purpose. However, they often rely on a large receptive field, LSTM or Transformer methods to capture…
Multistep traffic forecasting on road networks is a crucial task in successful intelligent transportation system applications. To capture the complex non-stationary temporal dynamics and spatial dependency in multistep traffic-condition…
To improve the efficiency of surgical trajectory segmentation for robot learning in robot-assisted minimally invasive surgery, this paper presents a fast unsupervised method using video and kinematic data, followed by a promoting procedure…
A steady momentum of innovations and breakthroughs has convincingly pushed the limits of unsupervised image representation learning. Compared to static 2D images, video has one more dimension (time). The inherent supervision existing in…
In this paper, we propose an end-to-end capsule network for pixel level localization of actors and actions present in a video. The localization is performed based on a natural language query through which an actor and action are specified.…
In many real-world applications, modeling both the internal structure of sets and their temporal relationships is essential for capturing complex underlying patterns. Sequential multiple-instance learning aims to address this challenge by…
We present a semi-supervised domain adaptation framework for brain vessel segmentation from different image modalities. Existing state-of-the-art methods focus on a single modality, despite the wide range of available cerebrovascular…
Temporal action localization is an important step towards video understanding. Most current action localization methods depend on untrimmed videos with full temporal annotations of action instances. However, it is expensive and…
Real-time video analysis remains a challenging problem in computer vision, requiring efficient processing of both spatial and temporal information while maintaining computational efficiency. Existing approaches often struggle to balance…
In this work\footnote {This work was supported in part by the National Science Foundation under grant IIS-1212948.}, we present a method to represent a video with a sequence of words, and learn the temporal sequencing of such words as the…
Our objective in this work is fine-grained classification of actions in untrimmed videos, where the actions may be temporally extended or may span only a few frames of the video. We cast this into a query-response mechanism, where each…
We introduce a novel approach for simultaneous self-supervised video alignment and action segmentation based on a unified optimal transport framework. In particular, we first tackle self-supervised video alignment by developing a fused…
We present an unsupervised representation learning approach that compactly encodes the motion dependencies in videos. Given a pair of images from a video clip, our framework learns to predict the long-term 3D motions. To reduce the…
The objective of this paper is self-supervised learning of video object segmentation. We develop a unified framework which simultaneously models cross-frame dense correspondence for locally discriminative feature learning and embeds…
Multimodal motion forecasting is inherently under-supervised: each training scene provides only one realized future, yet multiple plausible futures exist. This sparse supervision often leads to mode collapse (redundant hypotheses and…
This paper proposes a method for long-term action anticipation (LTA), the task of predicting action labels and their duration in a video given the observation of an initial untrimmed video interval. We build on an encoder-decoder…
Action recognition has become a rapidly developing research field within the last decade. But with the increasing demand for large scale data, the need of hand annotated data for the training becomes more and more impractical. One way to…
This paper describes a method based on a sequence-to-sequence learning (Seq2Seq) with attention and context preservation mechanism for voice conversion (VC) tasks. Seq2Seq has been outstanding at numerous tasks involving sequence modeling…