ViSAGE @ NTIRE 2026 Challenge on Video Saliency Prediction

• URL: http://arxiv.org/abs/2604.08613v1
• Date: Thu, 09 Apr 2026 02:50:21 GMT
• Title: ViSAGE @ NTIRE 2026 Challenge on Video Saliency Prediction
• Abstract summary: We propose Video Saliency with Adaptive Gated Experts (ViSAGE), a multi-expert ensemble framework.<n>ViSAGE aggregates diverse inductive biases to capture complex-temporal saliency in videos.<n>On the Private Test set, ViSAGE ranked first on two out of four evaluation metrics, and outperformed most competing solutions on the other two metrics.
• Score: 51.68198543931491
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this report, we present our champion solution for the NTIRE 2026 Challenge on Video Saliency Prediction held in conjunction with CVPR 2026. To exploit complementary inductive biases for video saliency, we propose Video Saliency with Adaptive Gated Experts (ViSAGE), a multi-expert ensemble framework. Each specialized decoder performs adaptive gating and modulation to refine spatio-temporal features. The complementary predictions from different experts are then fused at inference. ViSAGE thereby aggregates diverse inductive biases to capture complex spatio-temporal saliency cues in videos. On the Private Test set, ViSAGE ranked first on two out of four evaluation metrics, and outperformed most competing solutions on the other two metrics, demonstrating its effectiveness and generalization ability. Our code has been released at https://github.com/iLearn-Lab/CVPRW26-ViSAGE.

Related papers

• VADER: Adaptive Debiasing for Hallucination Mitigation in Video Large Language Models [30.792102059830274]
  Video-Adaptive Debiasing via Evidence Reweighting (VADER) is a training-free framework with two complementary modules.<n>Visual Focus Reallocation (VFR) automatically instantiates an intervention policy for each video-question input.<n> Selective Evidence Erasure (SEE) independently masks high-importance visual tokens in every frame.
  arXiv  Detail & Related papers  (2026-08-09T10:09:11Z)
• TempRet: Temporal Enhancement and Two-Stage Reranking for CVPR 2026 EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge [71.10535279591527]
  We present our solution, termed TempRet, to the CVPR 2026 EPIC-KITCHENS-100 MIR challenge.<n>Our approach builds upon a CLIP-based dual-encoder backbone and introduces two key components to address the temporal and cross-modal challenges.<n>Our method achieves 67.97% average mAP and 82.92% average nDCG on the EK-100 MIR benchmark.
  arXiv  Detail & Related papers  (2026-05-23T08:37:39Z)
• DIVE: Deep-search Iterative Video Exploration A Technical Report for the CVRR Challenge at CVPR 2025 [0.0]
  In this report, we present the winning solution that achieved the 1st place in the Complex Video Reasoning & Robustness Evaluation Challenge 2025.<n>It uses the Complex Video Reasoning and Robustness Evaluation Suite (CVRR-ES) benchmark, which consists of 214 unique videos and 2,400 question-answer pairs spanning 11 categories.<n>Our method, DIVE, adopts an iterative reasoning approach, in which each input question is semantically decomposed and solved through stepwise reasoning and progressive inference.
  arXiv  Detail & Related papers  (2025-06-27T04:05:12Z)
• Video-CoT: A Comprehensive Dataset for Spatiotemporal Understanding of Videos Based on Chain-of-Thought [19.792159494513424]
  Video comprehension is essential for various applications ranging from video analysis to interactive systems.<n>Despite advancements in vision-language models, these models often struggle to capture nuanced,temporal details.<n>To address this, we introduce Video-Thought, a groundbreaking dataset designed to enhance video understanding.
  arXiv  Detail & Related papers  (2025-06-10T14:08:56Z)
• AIM 2024 Challenge on Video Saliency Prediction: Methods and Results [105.09572982350532]
  This paper reviews the Challenge on Video Saliency Prediction at AIM 2024. The goal of the participants was to develop a method for predicting accurate saliency maps for the provided set of video sequences.
  arXiv  Detail & Related papers  (2024-09-23T08:59:22Z)
• VideoPrism: A Foundational Visual Encoder for Video Understanding [90.01845485201746]
  VideoPrism is a general-purpose video encoder that tackles diverse video understanding tasks with a single frozen model.<n>We pretrain VideoPrism on a heterogeneous corpus containing 36M high-quality video-caption pairs and 582M video clips with noisy parallel text.<n>We extensively test VideoPrism on four broad groups of video understanding tasks, from web video question answering to CV for science, achieving state-of-the-art performance on 31 out of 33 video understanding benchmarks.
  arXiv  Detail & Related papers  (2024-02-20T18:29:49Z)
• A Solution to CVPR'2023 AQTC Challenge: Video Alignment for Multi-Step Inference [51.26551806938455]
  Affordance-centric Question-driven Task Completion (AQTC) for Egocentric Assistant introduces a groundbreaking scenario. We present a solution for enhancing video alignment to improve multi-step inference. Our method secured the 2nd place in CVPR'2023 AQTC challenge.
  arXiv  Detail & Related papers  (2023-06-26T04:19:33Z)
• Perception Test: A Diagnostic Benchmark for Multimodal Video Models [78.64546291816117]
  We propose a novel multimodal video benchmark to evaluate the perception and reasoning skills of pre-trained multimodal models. The Perception Test focuses on skills (Memory, Abstraction, Physics, Semantics) and types of reasoning (descriptive, explanatory, predictive, counterfactual) across video, audio, and text modalities. The benchmark probes pre-trained models for their transfer capabilities, in a zero-shot / few-shot or limited finetuning regime.
  arXiv  Detail & Related papers  (2023-05-23T07:54:37Z)
• Anticipative Video Transformer [105.20878510342551]
  Anticipative Video Transformer (AVT) is an end-to-end attention-based video modeling architecture. We train the model jointly to predict the next action in a video sequence, while also learning frame feature encoders that are predictive of successive future frames' features.
  arXiv  Detail & Related papers  (2021-06-03T17:57:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.