SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.16272 · 2024

Beyond Uncertainty: Evidential Deep Learning for Robust Video Temporal Grounding

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Existing Video Temporal Grounding (VTG) models excel in accuracy but often overlook open-world challenges posed by open-vocabulary queries and untrimmed videos. This leads to unreliable predictions for noisy, corrupted, and out-of-distribution data. Adapting VTG models to dynamically estimate uncertainties based on user input can address this issue. To this end, we introduce SRAM, a robust network module that benefits from a two-stage cross-modal alignment task. More importantly, it integrates Deep Evidential Regression (DER) to explicitly and thoroughly quantify uncertainty during training, thus allowing the model to say "I do not know" in scenarios beyond its handling capacity. However, the direct application of traditional DER theory and its regularizer reveals structural flaws, leading to unintended constraints in VTG tasks. In response, we develop a simple yet effective Geom-regularizer that enhances the uncertainty learning framework from the ground up. To the best of our knowledge, this marks the first successful attempt of DER in VTG. Our extensive quantitative and qualitative results affirm the effectiveness, robustness, and interpretability of our modules and the uncertainty learning paradigm in VTG tasks. The code will be made available.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2408.16272")
get_code_for_paper("2408.16272")
have("2408.16272")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2408.16272.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2408.16272.svg)](https://syntology.ai/paper/2408.16272)

Connect an agent — have() is free.