Most video captioning models are designed to process short video clips of few seconds and output text describing low-level visual concepts (e.g., objects, scenes, atomic actions). However, most real-world videos last for minutes or hours and have a complex hierarchical structure spanning different temporal granularities. We propose Video ReCap, a recursive video captioning model that can process video inputs of dramatically different lengths (from 1 second to 2 hours) and output video captions at multiple hierarchy levels. The recursive video-language architecture exploits the synergy between different video hierarchies and can process hour-long videos efficiently. We utilize a curriculum learning training scheme to learn the hierarchical structure of videos, starting from clip-level captions describing atomic actions, then focusing on segment-level descriptions, and concluding with generating summaries for hour-long videos. Furthermore, we introduce Ego4D-HCap dataset by augmenting Ego4D with 8,267 manually collected long-range video summaries. Our recursive model can flexibly generate captions at different hierarchy levels while also being useful for other complex video understanding tasks, such as VideoQA on EgoSchema. Data, code, and models are available at: https://sites.google.com/view/vidrecap
We present LLoVi, a language-based framework for long-range video question-answering (LVQA). Unlike prior long-range video understanding methods, which are often costly and require specialized long-range video modeling design (e.g., memory queues, state-space layers, etc.), our approach uses a frame/clip-level visual captioner (e.g., BLIP2, LaViLa, LLaVA) coupled with a Large Language Model (GPT-3.5, GPT-4) leading to a simple yet surprisingly effective LVQA framework. Specifically, we decompose short and long-range modeling aspects of LVQA into two stages. First, we use a short-term visual captioner to generate textual descriptions of short video clips (0.5-8s in length) densely sampled from a long input video. Afterward, an LLM aggregates the densely extracted short-term captions to perform long-range temporal reasoning needed to understand the whole video and answer a question. To analyze what makes our simple framework so effective, we thoroughly evaluate various components of our system. Our empirical analysis reveals that the choice of the visual captioner and LLM is critical for good LVQA performance. Furthermore, we show that a specialized prompt that asks the LLM first to summarize the noisy short-term visual captions and then answer a given input question leads to a significant LVQA performance boost. On EgoSchema, which is best known as a very long-form video question-answering benchmark, our method achieves 50.3% accuracy, outperforming the previous best-performing approach by 18.1% (absolute gain). In addition, our approach outperforms the previous state-of-the-art by 4.1% and 3.1% on NeXT-QA and IntentQA. We also extend LLoVi to grounded LVQA and show that it outperforms all prior methods on the NeXT-GQA dataset. We will release our code at https://github.com/CeeZh/LLoVi.
We present a novel end-to-end method for long-form video temporal grounding to locate specific moments described by natural language queries. Prior long-video methods for this task typically contain two stages: proposal selection and grounding regression. However, the proposal selection of these methods is disjoint from the grounding network and is not trained end-to-end, which limits the effectiveness of these methods. Moreover, these methods operate uniformly over the entire temporal window, which is suboptimal given redundant and irrelevant features in long videos. In contrast to these prior approaches, we introduce RGNet, a unified network designed for jointly selecting proposals from hour-long videos and locating moments specified by natural language queries within them. To achieve this, we redefine proposal selection as a video-text retrieval task, i.e., retrieving the correct candidate videos given a text query. The core component of RGNet is a unified cross-modal RG-Encoder that bridges the two stages with shared features and mutual optimization. The encoder strategically focuses on relevant time frames using a sparse sampling technique. RGNet outperforms previous methods, demonstrating state-of-the-art performance on long video temporal grounding datasets MAD and Ego4D. The code is released at https://github.com/Tanveer81/RGNet
We present Ego-Exo4D, a diverse, large-scale multimodal multiview video dataset and benchmark challenge. Ego-Exo4D centers around simultaneously-captured egocentric and exocentric video of skilled human activities (e.g., sports, music, dance, bike repair). More than 800 participants from 13 cities worldwide performed these activities in 131 different natural scene contexts, yielding long-form captures from 1 to 42 minutes each and 1,422 hours of video combined. The multimodal nature of the dataset is unprecedented: the video is accompanied by multichannel audio, eye gaze, 3D point clouds, camera poses, IMU, and multiple paired language descriptions -- including a novel "expert commentary" done by coaches and teachers and tailored to the skilled-activity domain. To push the frontier of first-person video understanding of skilled human activity, we also present a suite of benchmark tasks and their annotations, including fine-grained activity understanding, proficiency estimation, cross-view translation, and 3D hand/body pose. All resources will be open sourced to fuel new research in the community.
The ability to distinguish between different movie scenes is critical for understanding the storyline of a movie. However, accurately detecting movie scenes is often challenging as it requires the ability to reason over very long movie segments. This is in contrast to most existing video recognition models, which are typically designed for short-range video analysis. This work proposes a State-Space Transformer model that can efficiently capture dependencies in long movie videos for accurate movie scene detection. Our model, dubbed TranS4mer, is built using a novel S4A building block, which combines the strengths of structured state-space sequence (S4) and self-attention (A) layers. Given a sequence of frames divided into movie shots (uninterrupted periods where the camera position does not change), the S4A block first applies self-attention to capture short-range intra-shot dependencies. Afterward, the state-space operation in the S4A block is used to aggregate long-range inter-shot cues. The final TranS4mer model, which can be trained end-to-end, is obtained by stacking the S4A blocks one after the other multiple times. Our proposed TranS4mer outperforms all prior methods in three movie scene detection datasets, including MovieNet, BBC, and OVSD, while also being $2\times$ faster and requiring $3\times$ less GPU memory than standard Transformer models. We will release our code and models.
This report describes our submission called "TarHeels" for the Ego4D: Object State Change Classification Challenge. We use a transformer-based video recognition model and leverage the Divided Space-Time Attention mechanism for classifying object state change in egocentric videos. Our submission achieves the second-best performance in the challenge. Furthermore, we perform an ablation study to show that identifying object state change in egocentric videos requires temporal modeling ability. Lastly, we present several positive and negative examples to visualize our model's predictions. The code is publicly available at: https://github.com/md-mohaiminul/ObjectStateChange
Most modern video recognition models are designed to operate on short video clips (e.g., 5-10s in length). Because of this, it is challenging to apply such models to long movie understanding tasks, which typically require sophisticated long-range temporal reasoning capabilities. The recently introduced video transformers partially address this issue by using long-range temporal self-attention. However, due to the quadratic cost of self-attention, such models are often costly and impractical to use. Instead, we propose ViS4mer, an efficient long-range video model that combines the strengths of self-attention and the recently introduced structured state-space sequence (S4) layer. Our model uses a standard Transformer encoder for short-range spatiotemporal feature extraction, and a multi-scale temporal S4 decoder for subsequent long-range temporal reasoning. By progressively reducing the spatiotemporal feature resolution and channel dimension at each decoder layer, ViS4mer learns complex long-range spatiotemporal dependencies in a video. Furthermore, ViS4mer is $2.63\times$ faster and requires $8\times$ less GPU memory than the corresponding pure self-attention-based model. Additionally, ViS4mer achieves state-of-the-art results in $7$ out of $9$ long-form movie video classification tasks on the LVU benchmark. Furthermore, we also show that our approach successfully generalizes to other domains, achieving competitive results on the Breakfast and the COIN procedural activity datasets. The code will be made publicly available.