Speed/accuracy trade-offs for modern convolutional object detectors
1 version
VR
Vivek Rathod
cs.CVcs.LGcs.AIcs.CLeess.IVcs.IRq-bio.PEstat.ML
On Valency
published · living versionsPreprints & journals
15 papers in the corpus · 2015–2026Rethinking Self-Distillation for Multi-Teacher Capability Merging
0 citations
LensVLM: Selective Context Expansion for Compressed Visual Representation of Text
0 citations
Apple Intelligence Foundation Language Models: Tech Report 2025
0 citations
AXLearn: Modular, Hardware-Agnostic Large Model Training
0 citations
Apple Intelligence Foundation Language Models
8 citations
The surprising impact of mask-head architecture on novel class segmentation
28 citations
DOPS: Learning to Detect 3D Objects and Predict their 3D Shapes
53 citations
RetinaTrack: Online Single Stage Joint Detection and Tracking
253 citations
Context R-CNN: Long Term Temporal Context for Per-Camera Object Detection
139 citations
Pooling Pyramid Network for Object Detection
16 citations
Semantic Instance Segmentation via Deep Metric Learning
189 citations
Deep Metric Learning via Facility Location
297 citations
Speed/accuracy trade-offs for modern convolutional object detectors
2,741 citations
Bayesian Dark Knowledge
195 citations
What's Cookin'? Interpreting Cooking Videos using Text, Speech and Vision
144 citations
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in beta. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.