The Visually-Guided Disambiguation Aggregation Aggregation (VGD-Agg) framework is proposed, a framework based on a dual-branch fast-slow architecture that enhances discriminability via two learnable tokens and achieves state-of-the-art results on the proposed benchmarks.
Abstract
Video Temporal Grounding (VTG) faces significant challenges when natural language queries must distinguish between multiple events involving visually similar entities, particularly when relying on fine-grained visual attributes that are difficult to describe accurately in words alone. To address this, we introduce Image-Disambiguated Video Temporal Grounding (ID-VTG), a task that leverages multimodal queries combining a reference image and a text description to precisely localize segments where a specific instance performs a described action. To facilitate research, we construct two benchmarks: IDVTG-Gym, focusing on fine-grained, compositionally ordered gymnastics actions with athletes in similar uniforms; and IDVTG-InternVid, an open-world dataset featuring diverse entities (e.g., humans, animals, fictional characters) and significant temporal distractors. Methodologically, we propose the Visually-Guided Disambiguation Aggregation (VGD-Agg) framework based on a dual-branch fast-slow architecture. The fast branch efficiently generates preliminary event proposals, while the slow branch performs fine-grained frame-level matching between video frames and the reference image. We enhance discriminability via two learnable tokens: a Compare Token, which represents hard negatives to probe for the presence of the target instance (as referred to by the query image), and a Depress Value, which represents text-irrelevant events. Proposals that the Compare Token identifies as lacking the target instance are pushed toward the Depress Value, thus easing disambiguation via the text query. Extensive experiments validate our approach, which achieves state-of-the-art results on the proposed benchmarks. Code is available at https://github.com/oceanflowlab/ID-VTG.
Despite the impressive progress of recent MLLMs on spatio-temporal video grounding (STVG), existing evaluations and training data focus primarily on simple queries. They largely overlook the compositional queries prevalent in real-world scenarios, where a target must be disambiguated by jointly reasoning about its attributes and relations to other entities. To bridge this gap, we propose Compositional Spatio-Temporal Video Grounding (CompSTVG), a task that requires models to process complex textual queries where every intertwined attribute and relational cue is essential for disambiguation. To facilitate this task at scale, we build a synthetic data engine that leverages a spatio-temporal scene graph as a difficulty measure and casts difficulty-controlled query synthesis as a constraint programming problem, producing difficulty-graded data for both evaluation and training. Built on this engine, we introduce STVG-CompBench, a benchmark stratified by explicit difficulty levels that jointly capture temporal complexity and spatial interference. Evaluating 11 representative STVG models on STVG-CompBench reveals that current models perform poorly on compositional queries, exhibiting a sharp performance drop that is typically obscured by overall dataset-level averages. We further construct synthetic training data and propose CurrSTVG, a curriculum reinforcement learning framework that delivers consistent gains, with the largest improvements observed on the most challenging compositional queries.
Xing-Jian Wang, Shijian Wang, Yi-Bo Wang et al.· 0 citations
Visual aliasing, also known as the doppelganger problem, remains a key challenge for structure-from-motion (SfM): visually similar but physically distinct surfaces can produce incorrect image matches and degrade reconstruction quality. Previous work mitigates this issue with geometry-aware foundation-model features, but places a heavy transformer classifier on top of the backbone, making large-scale disambiguation expensive. We introduce XDG, an efficient visual disambiguation model designed for scalable SfM. Our key observation is that a 3D foundation model already performs the cross-view geometric reasoning necessary for visual disambiguation, so doppelganger classification should adapt the backbone representation directly rather than relearn pair reasoning in a separate heavy decoder. XDG fine-tunes Depth Anything 3 with lightweight LoRA adapters and repurposes its camera tokens as compact pair-level classification tokens. A compact MLP head predicts whether a candidate image pair observes the same 3D surface. Extensive experiments show that XDG provides a favorable accuracy-efficiency tradeoff: it remains competitive with the state-of-the-art disambiguation method across pairwise and reconstruction benchmarks and delivers more than a 3x inference speedup. On individual LaMAR scenes containing thousands of images, XDG saves more than 10 hours of visual disambiguation processing. Code is available at https://github.com/xtcpete/xdg.
Gonglin Chen, Ben Southall, Hanyuan Xiao et al.· 0 citations
Across seven benchmarks, TimeLens2-2B outperforms all size-matched baselines on every benchmark, while the 4B and 8B variants achieve state-of-the-art performance, surpassing open-source models with up to 397B parameters.
Referring Video Object Segmentation (RVOS) aims to segment the target objects specified in human instructions. Previous approaches typically rely on explicit human instructions that contain target categories or salient appearance descriptions. These approaches tend to fail when the instructions require temporal video understanding and complex relational reasoning. In this work, we present RViSeg, a reasoning-centric video object segmentation model that leverages the reasoning capability of Multi-modal Large Language Models (MLLM) to handle complex queries. The primary challenge lies in enabling MLLM to perform efficient pixel-level video perception. To tackle this challenge, we introduce a novel Spatial Token Merge (STM) module that consolidates lengthy video tokens into compact region-level clusters, while preserving essential spatial details. This structured representation enables MLLM to infer user intention by interleaving spatial and temporal visual information. Furthermore, we propose a Query-based Target Retrieval (QTR) module that utilizes learnable tokens as the target identity for mask prediction. By propagating these instance-specific tokens both intra-clip and inter-clip, our RViSeg effectively encodes object motion, ensuring spatio-temporal consistency in segmentation results. To facilitate training and evaluation, we construct InstructVideo, a single- and multiple-object reasoning video segmentation benchmark. Comprehensive experiments demonstrate the effectiveness of the proposed components.
Yanyan Shao, Shuting He, Gengze Zhou et al.· IEEE Transactions on Image P...· 0 citations
This work proposes REcognition-based Zero-shot Extraction (REZE), a simple training-free method that splits the video into short clips, asks the model for a clip-level confidence score for the query, and uses a deterministic algorithm to convert the resulting score curve into the output required by the task.
Boyang Albert Li, Chenhui Gou, Jianfei Cai· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
