Large language models (LLMs) excel at retrieving information from lengthy text, but their vision-language counterparts (VLMs) face difficulties with hour-long videos, especially for temporal grounding. Specifically, these VLMs are constrained by frame limitations, often losing essential temporal details needed for accurate event localization in extended video content. We propose ReVisionLLM, a recursive vision-language model designed to locate events in hour-long videos. Inspired by human search strategies, our model initially targets broad segments of interest, progressively revising its focus to pinpoint exact temporal boundaries. Our model can seamlessly handle videos of vastly different lengths, from minutes to hours. We also introduce a hierarchical training strategy that starts with short clips to capture distinct events and progressively extends to longer videos. To our knowledge, ReVisionLLM is the first VLM capable of temporal grounding in hour-long videos, outperforming previous state-of-the-art methods across multiple datasets by a significant margin (+2.6% [email omitted] on MAD). The code is available at https://github.com/Tanveer81/ReVisionLLM.
Temporal grounding aims to locate a target video moment that semantically corresponds to the given sentence query in an untrimmed video. However, recent works find that existing methods suffer a severe temporal bias problem. These methods do not reason the target moment locations based on the visual-textual semantic alignment but over-rely on the temporal biases of queries in training sets. To this end, this paper proposes a novel training framework for grounding models to use shuffled videos to address temporal bias problem without losing grounding accuracy. Our framework introduces two auxiliary tasks, cross-modal matching and temporal order discrimination, to promote the grounding model training. The cross-modal matching task leverages the content consistency between shuffled and original videos to force the grounding model to mine visual contents to semantically match queries. The temporal order discrimination task leverages the difference in temporal order to strengthen the understanding of long-term temporal contexts. Extensive experiments on Charades-STA and ActivityNet Captions demonstrate the effectiveness of our method for mitigating the reliance on temporal biases and strengthening the model's generalization ability against the different temporal distributions. Code is available at https://github.com/haojc/ShufflingVideosForTSG.
We consider the problem of localizing a spatio-temporal tube in a video corresponding to a given text query. This is a challenging task that requires the joint and efficient modeling of temporal, spatial and multi-modal interactions. To address this task, we propose TubeDETR, a transformer-based architecture inspired by the recent success of such models for text-conditioned object detection. Our model notably includes: (i) an efficient video and text encoder that models spatial multi-modal interactions over sparsely sampled frames and (ii) a space-time decoder that jointly performs spatio-temporal localization. We demonstrate the advantage of our proposed components through an extensive ablation study. We also evaluate our full approach on the spatio-temporal video grounding task and demonstrate improvements over the state of the art on the challenging VidSTG and HC-STVG benchmarks. Code and trained models are publicly available at https://antoyang.github.io/tubedetr.html.
Temporal Moment Localization (TML) in untrimmed videos is a challenging task in the field of multimedia, which aims at localizing the start and end points of the activity in the video, described by a sentence query. Existing methods mainly focus on mining the correlation between video and sentence representations or investigating the fusion manner of the two modalities. These works mainly understand the video and sentence coarsely, ignoring the fact that a sentence can be understood from various semantics, and the dominant words affecting the moment localization in the semantics are the action and object reference. Toward this end, we propose a Hierarchical Deep Residual Reasoning (HDRR) model, which decomposes the video and sentence into multi-level representations with different semantics to achieve a finer-grained localization. Furthermore, considering that videos with different resolution and sentences with different length have different difficulty in understanding, we design the simple yet effective Res-BiGRUs for feature fusion, which is able to grasp the useful information in a self-adapting manner. Extensive experiments conducted on Charades-STA and ActivityNet-Captions datasets demonstrate the superiority of our HDRR model compared with other state-of-the-art methods.
We address the problem of language-based temporal localization of moments in untrimmed videos. Compared to temporal localization with fixed categories, this problem is more challenging as the language-based queries have no predefined activity classes and may also contain complex descriptions. Current state-of-the-art model MAC addresses it by mining activity concepts from both video and language modalities. This method encodes the semantic activity concepts from the verb/object pair in a language query and leverages visual activity concepts from video activity classification prediction scores. We propose "Multi-faceted VideoMoment Localizer" (MML), an extension of MAC model by the introduction of visual object evidence via object segmentation masks and video understanding features via video captioning. Furthermore, we improve language modelling in sentence embedding. We experimented on Charades-STA dataset and identified that MML outperforms MAC baseline by 4.93% and 1.70% on R@1 and R@5metrics respectively. Our code and pre-trained model are publicly available at https://github.com/madhawav/MML.
We address the problem of language-based temporal localization in untrimmed videos. Compared to temporal localization with fixed categories, this problem is more challenging as the language-based queries not only have no pre-defined activity list but also may contain complex descriptions. Previous methods address the problem by considering features from video sliding windows and language queries and learning a subspace to encode their correlation, which ignore rich semantic cues about activities in videos and queries. We propose to mine activity concepts from both video and language modalities by applying the actionness score enhanced Activity Concepts based Localizer (ACL). Specifically, the novel ACL encodes the semantic concepts from verb-obj pairs in language queries and leverages activity classifiers' prediction scores to encode visual concepts. Besides, ACL also has the capability to regress sliding windows as localization results. Experiments show that ACL significantly outperforms state-of-the-arts under the widely used metric, with more than 5% increase on both Charades-STA and TACoS datasets.