Picture for Ali Athar

Ali Athar

ViCaS: A Dataset for Combining Holistic and Pixel-level Video Understanding using Captions with Grounded Segmentation

Add code
Dec 12, 2024
Viaarxiv icon

4D-Former: Multimodal 4D Panoptic Segmentation

Add code
Nov 17, 2023
Figure 1 for 4D-Former: Multimodal 4D Panoptic Segmentation
Figure 2 for 4D-Former: Multimodal 4D Panoptic Segmentation
Figure 3 for 4D-Former: Multimodal 4D Panoptic Segmentation
Figure 4 for 4D-Former: Multimodal 4D Panoptic Segmentation
Viaarxiv icon

TarViS: A Unified Approach for Target-based Video Segmentation

Add code
Jan 06, 2023
Figure 1 for TarViS: A Unified Approach for Target-based Video Segmentation
Figure 2 for TarViS: A Unified Approach for Target-based Video Segmentation
Figure 3 for TarViS: A Unified Approach for Target-based Video Segmentation
Figure 4 for TarViS: A Unified Approach for Target-based Video Segmentation
Viaarxiv icon

BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in Video

Add code
Sep 25, 2022
Figure 1 for BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in Video
Figure 2 for BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in Video
Figure 3 for BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in Video
Figure 4 for BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in Video
Viaarxiv icon

Differentiable Soft-Masked Attention

Add code
Jun 01, 2022
Figure 1 for Differentiable Soft-Masked Attention
Figure 2 for Differentiable Soft-Masked Attention
Figure 3 for Differentiable Soft-Masked Attention
Figure 4 for Differentiable Soft-Masked Attention
Viaarxiv icon

HODOR: High-level Object Descriptors for Object Re-segmentation in Video Learned from Static Images

Add code
Dec 16, 2021
Figure 1 for HODOR: High-level Object Descriptors for Object Re-segmentation in Video Learned from Static Images
Figure 2 for HODOR: High-level Object Descriptors for Object Re-segmentation in Video Learned from Static Images
Figure 3 for HODOR: High-level Object Descriptors for Object Re-segmentation in Video Learned from Static Images
Figure 4 for HODOR: High-level Object Descriptors for Object Re-segmentation in Video Learned from Static Images
Viaarxiv icon

D^2Conv3D: Dynamic Dilated Convolutions for Object Segmentation in Videos

Add code
Nov 15, 2021
Figure 1 for D^2Conv3D: Dynamic Dilated Convolutions for Object Segmentation in Videos
Figure 2 for D^2Conv3D: Dynamic Dilated Convolutions for Object Segmentation in Videos
Figure 3 for D^2Conv3D: Dynamic Dilated Convolutions for Object Segmentation in Videos
Figure 4 for D^2Conv3D: Dynamic Dilated Convolutions for Object Segmentation in Videos
Viaarxiv icon

Making a Case for 3D Convolutions for Object Segmentation in Videos

Add code
Aug 26, 2020
Figure 1 for Making a Case for 3D Convolutions for Object Segmentation in Videos
Figure 2 for Making a Case for 3D Convolutions for Object Segmentation in Videos
Figure 3 for Making a Case for 3D Convolutions for Object Segmentation in Videos
Figure 4 for Making a Case for 3D Convolutions for Object Segmentation in Videos
Viaarxiv icon

STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos

Add code
Apr 10, 2020
Figure 1 for STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos
Figure 2 for STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos
Figure 3 for STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos
Figure 4 for STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos
Viaarxiv icon

Multiple People Tracking Using Hierarchical Deep Tracklet Re-identification

Add code
Nov 17, 2018
Figure 1 for Multiple People Tracking Using Hierarchical Deep Tracklet Re-identification
Figure 2 for Multiple People Tracking Using Hierarchical Deep Tracklet Re-identification
Figure 3 for Multiple People Tracking Using Hierarchical Deep Tracklet Re-identification
Figure 4 for Multiple People Tracking Using Hierarchical Deep Tracklet Re-identification
Viaarxiv icon