Search Results for author:
Found 5 papers, 1 papers with code
Frustratingly Simple but Effective Zero-shot Detection and Segmentation: Analysis and a Strong Baseline
Methods for object detection and segmentation often require abundant instance-level annotations for training, which are time-consuming and expensive to collect.
Efficient Video Instance Segmentation via Tracklet Query and Proposal
In addition, VisTR is not fully end-to-end learnable in multiple video clips as it requires a hand-crafted data association to link instance tracklets between successive clips.
TesseTrack: End-to-End Learnable Multi-Person Articulated 3D Pose Tracking
At the core of our approach is a novel spatio-temporal formulation that operates in a common voxelized feature space aggregated from single- or multiple camera views.
Ranked #1 on
3D Human Pose Estimation
on Panoptic
(using extra training data)
Energy-Based Learning for Scene Graph Generation
The proposed formulation allows for efficiently incorporating the structure of scene graphs in the output space.
Ranked #3 on
Scene Graph Classification
on Visual Genome
(R@20 metric)
MILA: Multi-Task Learning from Videos via Efficient Inter-Frame Attention
We embed the attention module in a ``slow-fast'' architecture, where the slower network runs on sparsely sampled keyframes and the light-weight shallow network runs on non-keyframes at a high frame rate.
