42 citations · 161 across the 16 of their papers we have counts for
19 papers
HMD-NeMo: Online 3D Avatar Motion Generation From Sparse Observations
Sadegh Aliakbarian, Fatemeh Saleh, David Collier +2
Generating both plausible and accurate full body avatar motion is the key to the quality of immersive experiences in mixed reality scenarios. Head-Mounted Devices (HMDs) typically…
Effective Self-supervised Pre-training on Low-compute Networks without Distillation
Fuwen Tan, Fatemeh Saleh, Brais Martinez
Despite the impressive progress of self-supervised learning (SSL), its applicability to low-compute networks has received limited attention. Reported performance has trailed behind…
iBoot: Image-bootstrapped Self-Supervised Video Representation Learning
Fatemeh Saleh, Fuwen Tan, Adrian Bulat +2
Learning visual representations through self-supervision is an extremely challenging task as the network needs to sieve relevant patterns from spurious distractors without the acti…
JRDB-Act: A Large-scale Dataset for Spatio-temporal Action, Social Group and Activity Detection
Mahsa Ehsanpour, Fatemeh Saleh, Silvio Savarese +2
The availability of large-scale video action understanding datasets has facilitated advances in the interpretation of visual scenes containing people. However, learning to recognis…
Probabilistic Tracklet Scoring and Inpainting for Multiple Object Tracking
Fatemeh Saleh, Sadegh Aliakbarian, Hamid Rezatofighi +2
Despite the recent advances in multiple object tracking (MOT), achieved by joint detection and tracking, dealing with long occlusions remains a challenge. This is due to the fact t…
Uncertainty Inspired RGB-D Saliency Detection
Jing Zhang, Deng-Ping Fan, Yuchao Dai +4
We propose the first stochastic framework to employ uncertainty for RGB-D saliency detection by learning from the data labeling process. Existing RGB-D saliency detection models tr…
Joint Learning of Social Groups, Individuals Action and Sub-group Activities in Videos
Mahsa Ehsanpour, Alireza Abedin, Fatemeh Saleh +3
The state-of-the art solutions for human activity understanding from a video stream formulate the task as a spatio-temporal problem which requires joint localization of all individ…
The IKEA ASM Dataset: Understanding People Assembling Furniture through Actions, Objects and Pose
Yizhak Ben-Shabat, Xin Yu, Fatemeh Sadat Saleh +4
The availability of a large labeled dataset is a key requirement for applying deep learning methods to solve various computer vision tasks. In the context of understanding human ac…
ArTIST: Autoregressive Trajectory Inpainting and Scoring for Tracking
Fatemeh Saleh, Sadegh Aliakbarian, Mathieu Salzmann +1
One of the core components in online multiple object tracking (MOT) frameworks is associating new detections with existing tracklets, typically done via a scoring function. Despite…
UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders
Jing Zhang, Deng-Ping Fan, Yuchao Dai +4
In this paper, we propose the first framework (UCNet) to employ uncertainty for RGB-D saliency detection by learning from the data labeling process. Existing RGB-D saliency detecti…
Contextually Plausible and Diverse 3D Human Motion Prediction
Sadegh Aliakbarian, Fatemeh Sadat Saleh, Lars Petersson +2
We tackle the task of diverse 3D human motion prediction, that is, forecasting multiple plausible future 3D poses given a sequence of observed 3D poses. In this context, a popular…
Proposal-free Temporal Moment Localization of a Natural-Language Query in Video using Guided Attention
Cristian Rodriguez-Opazo, Edison Marrese-Taylor, Fatemeh Sadat Saleh +2
This paper studies the problem of temporal moment localization in a long untrimmed video using natural language as the query. Given an untrimmed video and a sentence as the query,…
Learning Variations in Human Motion via Mix-and-Match Perturbation
Mohammad Sadegh Aliakbarian, Fatemeh Sadat Saleh, Mathieu Salzmann +3
Human motion prediction is a stochastic process: Given an observed sequence of poses, multiple future motions are plausible. Existing approaches to modeling this stochasticity typi…
VIENA2: A Driving Anticipation Dataset
Mohammad Sadegh Aliakbarian, Fatemeh Sadat Saleh, Mathieu Salzmann +3
Action anticipation is critical in scenarios where one needs to react before the action is finalized. This is, for instance, the case in automated driving, where a car needs to, e.…
Effective Use of Synthetic Data for Urban Scene Semantic Segmentation
Fatemeh Sadat Saleh, Mohammad Sadegh Aliakbarian, Mathieu Salzmann +2
Training a deep network to perform semantic segmentation requires large amounts of labeled data. To alleviate the manual effort of annotating real images, researchers have investig…
Bringing Background into the Foreground: Making All Classes Equal in Weakly-supervised Video Semantic Segmentation
Fatemeh Sadat Saleh, Mohammad Sadegh Aliakbarian, Mathieu Salzmann +2
Pixel-level annotations are expensive and time-consuming to obtain. Hence, weak supervision using only image tags could have a significant impact in semantic segmentation. Recent y…
Incorporating Network Built-in Priors in Weakly-supervised Semantic Segmentation
Fatemeh Sadat Saleh, Mohammad Sadegh Aliakbarian, Mathieu Salzmann +3
Pixel-level annotations are expensive and time consuming to obtain. Hence, weak supervision using only image tags could have a significant impact in semantic segmentation. Recently…
Deep Action- and Context-Aware Sequence Learning for Activity Recognition and Anticipation
Mohammad Sadegh Aliakbarian, Fatemehsadat Saleh, Basura Fernando +3
Action recognition and anticipation are key to the success of many computer vision applications. Existing methods can roughly be grouped into those that extract global, context-awa…
Built-in Foreground/Background Prior for Weakly-Supervised Semantic Segmentation
Fatemehsadat Saleh, Mohammad Sadegh Ali Akbarian, Mathieu Salzmann +3
Pixel-level annotations are expensive and time consuming to obtain. Hence, weak supervision using only image tags could have a significant impact in semantic segmentation. Recently…