AI Paper Atlas

Research map / Video / Video segmentation and tracking

Latent-INR: A Flexible Framework for Implicit Representations of Videos with Discriminative Semantics

Shishira R Maiya, Anubhav Gupta, Matthew A Gwilliam, Max Ehrlich, Abhinav Shrivastava

ECCV 2024 · Video › Video segmentation and tracking · approach: Neural video representations · 8 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
add CLIP alignment loss on latents (lambda 1e-3 to 1) (ablation)Latent-INR · MSR-VTTT2V R@1: 0.1 -> 30.2Improved
increase CLIP loss weight lambda from 0 to 1.0 (ablation)Latent-INR · MSR-VTTReconstruction PSNR: 30.03 -> 28.61Hurt
increase CLIP lambda beyond 0.01 (ablation)Latent-INR · MSR-VTTT2V R@1: 30.2 -> 29.7 / 30.2No clear effect
use latent-space interpolation through hypernetwork instead of time or weight interpolation of other INRsvideo INR · Bunny alpha=8PSNR: 18.67 -> 25.88 (vs NIRVANA)Improved
retrieve with Latent-INR latents aligned to CLIP instead of CLIP featuresretrieval · COIN segment-levelR@1: 6.60 -> 6.40No clear effect
retrieve with Latent-INR latents instead of CLIP featuresretrieval · HowTo100m subset segment-levelR@10: 40.85 -> 48.60Improved
use Fourier features instead of hash-grid positional encoding (ablation)Latent-INR · UVG compressiontraining speed / reconstruction: up to 30% faster trainingMixed
use larger patch sizes in patch-centroid model (ablation)Latent-INR · UVGPSNRHurt
increase latent dimension beyond 512 (ablation)Latent-INR · UVG bosphorePSNR vs bitrateNo clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

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