Semantic object segmentation via detection in weakly labeled video

81 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Object-Proposal Evaluation Protocol is ‘Gameable’ (2015, background): “These windows are then scored for the presence of an object based on the image features from the windows.”
Learning Video Object Segmentation from Static Images (2016, methodology): “In particular, we compare to FCP [35], Z15 [56], NLC [15] and W16 [50] which build a global graph structure over object proposal segments, and then infer a consistent segmentation.”
Weakly Supervised Semantic Segmentation Using Web-Crawled Videos (2017, methodology): “Interestingly, our method outperforms approaches using object detector trained on bounding box annotations [9, 40] that require stronger supervision than image-level labels.”
Learning Video Object Segmentation From Unlabeled Videos (2020, methodology): “Supervision Non Learning Unsupervised Learning Weakly-supervised Learning Method CRANE[47] NLC[7] FST[33] ARP[19] Motion Masks[34] TSN[17] Ours SOSD[75] BBF[42] COSEG[50] Ours”
Instance-Level Video Segmentation from Object Tracks (2016, background): “The use of object detectors as weak cues for semantic video segmentation been explored in [50].”
STFCN: Spatio-Temporal FCN for Semantic Video Segmentation (2016, methodology): “Mean IU is a segmentation performance measure that quantiﬁes the overlap of two objects by calculating the ratio of the area of intersection to the area of unions [24,48].”