- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This manuscript proposes a dual-memory framework for retrieving video moments in streaming videos. It uses two modules: one for short-term context within the current video, and another for long-term action knowledge across videos. This helps compensate for missing future frames and improves temporal localization. Experiments on multiple benchmarks confirm its effectiveness.
Critical strengths
- The paper presents a clear motivation and a well-structured framework. The overall methodology is clearly explained and effectively illustrated, making the proposed approach easy to understand.
- The paper provides extensive experiments and ablation studies across multiple benchmarks and backbone models, demonstrating the effectiveness of the proposed method.
Critical weaknesses
- Memory-based temporal modeling and future anticipation have already been explored in streaming video moment retrieval (e.g., TSGSV [1] and HEM [2]). While the proposed Header–Slider structure offers a novel way to organize cross-video action knowledge, its distinct contribution over these closely related methods remains insufficiently established.
- In Eq. (10), current visual features and static memory are concatenated with learnable future tokens as queries for cross-attention. However, under standard cross-attention, future query outputs do not directly incorporate information from other query tokens. It is therefore unclear how retrieved action trends are effectively adapted to the current scene.
- While Table 11 shows that retrieving subsequent memory features improves localization, it does not verify whether these features accurately capture future action dynamics. Furthermore, the stage-wise analysis in Table 10 lacks baseline comparisons, making it difficult to assess if the method specifically enhances localization during early observation stages where future context is most limited.
- Table 7 indicates that Dual-Memory nearly doubles the parameter count (7.91M to 14.91M). Without a parameter-matched baseline (e.g., a larger backbone or simpler memory module with comparable capacity), it is unclear whether the performance gains stem from the proposed memory design or merely the increased model capacity.
[1] Gan T, Wang X, Sun Y, et al. Temporal sentence grounding in streaming videos[C]//Proceedings of the 31st ACM International Conference on Multimedia. 2023: 4637-4646. [2] Zheng M, Peng Y, Sun B, et al. Hierarchical event memory for accurate and low-latency online video temporal grounding[C]//2025 IEEE/CVF International Conference on Computer Vision (ICCV). IEEE, 2025: 21589-21599.
Questions for authors
- Clarify the core methodological novelty compared with existing memory-based approaches, particularly TSGSV and HEM, and highlight the unique contributions of the proposed dual-memory framework.
- Explain how Eq. (10) incorporates scene-specific static information and current visual features into the generated future tokens, particularly given the standard formulation of cross-attention.
- Provide further evidence that the retrieved future features accurately represent future action dynamics, rather than simply serving as additional contextual information.
- Clarify whether the proposed framework provides greater improvements during the early stages of action observation, where future information is most limited.
- Discuss the influence of increased model capacity and whether comparable improvements could be achieved using a parameter-matched backbone without the proposed dual-memory mechanism.