AI Paper Atlas

Research map / Video / Video segmentation and tracking

TASED-Net: Temporally-Aggregating Spatial Encoder-Decoder Network for Video Saliency Detection

Kyle Min, Jason J. Corso

ICCV 2019 · Video › Video segmentation and tracking · approach: Self-supervised video representation learning · 207 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use late two-step instead of early two-step aggregation (ablation)TASED-Net (T=32) · DHF1K valNSS: 2.673 -> 2.706Improved
use late two-step instead of late aggregation (ablation)TASED-Net (T=32) · DHF1K valNSS: 2.618 -> 2.706Improved
add Kinetics pre-training of the encoder (ablation)TASED-Net · DHF1K valNSS: about 0.5 NSSImproved
add auxiliary pooling with max-unpooling instead of trilinear upsampling (ablation)TASED-Net · DHF1K valNSS: 2.452 -> 2.706Improved
add auxiliary pooling with max-unpooling instead of transposed convolution (ablation)TASED-Net · DHF1K valNSS: 2.598 -> 2.706Improved
increase clip length from 16 to 32 frames (ablation)TASED-Net · DHF1K valNSS: 2.622 -> 2.706Improved
increase clip length from 32 to 64 frames (ablation)TASED-Net · DHF1K valNSS: 2.706 -> 2.554Hurt
reduce clip length from 32 to 4 frames (ablation)TASED-Net · DHF1K valNSS: 2.706 -> 2.434Hurt
add two more stride-1 transposed convolutions per spatial decoding block (denser decoder) (ablation)TASED-Net · DHF1K valNSSHurt
predict multiple saliency maps per window instead of a single map (ablation)TASED-Net · DHF1K valNSSHurt
use TASED-Net over ACLNetTASED-Net · DHF1K testNSS: 2.354 -> 2.667Improved
use TASED-Net over ACLNetTASED-Net · Hollywood2 testNSS: 3.086 -> 3.302Improved

Later papers that compared with this method

1 later accepted paper reports TASED-Net as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy