Related papers: Memory Storyboard: Leveraging Temporal Segmentatio…
Understanding temporal dynamics of video is an essential aspect of learning better video representations. Recently, transformer-based architectural designs have been extensively explored for video tasks due to their capability to capture…
This work proposes a self-supervised learning system for segmenting rigid objects in RGB images. The proposed pipeline is trained on unlabeled RGB-D videos of static objects, which can be captured with a camera carried by a mobile robot. A…
Future activity anticipation is a challenging problem in egocentric vision. As a standard future activity anticipation paradigm, recursive sequence prediction suffers from the accumulation of errors. To address this problem, we propose a…
Artificial autonomous agents and robots interacting in complex environments are required to continually acquire and fine-tune knowledge over sustained periods of time. The ability to learn from continuous streams of information is referred…
This paper presents a new self-supervised video representation learning framework, ARVideo, which autoregressively predicts the next video token in a tailored sequence order. Two key designs are included. First, we organize autoregressive…
Episodic memory retrieval enables wearable cameras to recall objects or events previously observed in video. However, existing formulations assume an "offline" setting with full video access at query time, limiting their applicability in…
This paper is on long-term video understanding where the goal is to recognise human actions over long temporal windows (up to minutes long). In prior work, long temporal context is captured by constructing a long-term memory bank consisting…
We explore self-supervised models that can be potentially deployed on mobile devices to learn general purpose audio representations. Specifically, we propose methods that exploit the temporal context in the spectrogram domain. One method…
Temporal action segmentation in videos has drawn much attention recently. Timestamp supervision is a cost-effective way for this task. To obtain more information to optimize the model, the existing method generated pseudo frame-wise labels…
We present a self-supervised approach using spatio-temporal signals between video frames for action recognition. A two-stream architecture is leveraged to tangle spatial and temporal representation learning. Our task is formulated as both a…
Semi-Supervised Learning can be more beneficial for the video domain compared to images because of its higher annotation cost and dimensionality. Besides, any video understanding task requires reasoning over both spatial and temporal…
This paper presents a novel approach for temporal and semantic segmentation of edited videos into meaningful segments, from the point of view of the storytelling structure. The objective is to decompose a long video into more manageable…
Self-supervised learning is an effective way for label-free model pre-training, especially in the video domain where labeling is expensive. Existing self-supervised works in the video domain use varying experimental setups to demonstrate…
This paper addresses the task of segmenting moving objects in unconstrained videos. We introduce a novel two-stream neural network with an explicit memory module to achieve this. The two streams of the network encode spatial and temporal…
Self-supervised learning has emerged as a powerful paradigm for label-free model pretraining, particularly in the video domain, where manual annotation is costly and time-intensive. However, existing self-supervised approaches employ…
Robust video scene classification models should capture the spatial (pixel-wise) and temporal (frame-wise) characteristics of a video effectively. Transformer models with self-attention which are designed to get contextualized…
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…
Despite their irresistible success, deep learning algorithms still heavily rely on annotated data. On the other hand, unsupervised settings pose many challenges, especially about determining the right inductive bias in diverse scenarios.…
We leverage unsupervised learning of depth, egomotion, and camera intrinsics to improve the performance of single-image semantic segmentation, by enforcing 3D-geometric and temporal consistency of segmentation masks across video frames. The…
In low-level video analyses, effective representations are important to derive the correspondences between video frames. These representations have been learned in a self-supervised fashion from unlabeled images or videos, using carefully…