Proposal-level spatio-temporal context aggregation for video object detection achieves 80.3% mAP on ImageNet VID, improving Faster R-CNN baseline by 5.8%.
Seq-NMS for Video Object Detection
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
Video object detection is challenging because objects that are easily detected in one frame may be difficult to detect in another frame within the same clip. Recently, there have been major advances for doing object detection in a single image. These methods typically contain three phases: (i) object proposal generation (ii) object classification and (iii) post-processing. We propose a modification of the post-processing phase that uses high-scoring object detections from nearby frames to boost scores of weaker detections within the same clip. We show that our method obtains superior results to state-of-the-art single image object detection techniques. Our method placed 3rd in the video object detection (VID) task of the ImageNet Large Scale Visual Recognition Challenge 2015 (ILSVRC2015).
fields
cs.CV 2representative citing papers
MR2-ByteTrack maintains high accuracy in video object detection on MCUs by combining multi-resolution processing, ByteTrack for frame linking, and Rescore for confidence aggregation, achieving up to 55% energy savings and real-time performance for both CNN and Transformer models.
citing papers explorer
-
Object Detection in Video with Spatial-temporal Context Aggregation
Proposal-level spatio-temporal context aggregation for video object detection achieves 80.3% mAP on ImageNet VID, improving Faster R-CNN baseline by 5.8%.
-
MR2-ByteTrack: CNN and Transformer-based Video Object Detection for AI-augmented Embedded Vision Sensor Nodes
MR2-ByteTrack maintains high accuracy in video object detection on MCUs by combining multi-resolution processing, ByteTrack for frame linking, and Rescore for confidence aggregation, achieving up to 55% energy savings and real-time performance for both CNN and Transformer models.