Neptune: The Long Orbit to Benchmarking Long Video Understanding

This paper describes a semi-automatic pipeline to generate challenging question-answer-decoy sets for understanding long videos. Many existing video datasets and models are focused on short clips (10s-30s). While some long video datasets do exist, they can often be solved by powerful image models applied per frame (and often to very few frames) in a video, and are usually manually annotated at high cost. In order to mitigate both these problems, we propose a scalable dataset creation pipeline which leverages large models (VLMs and LLMs), to automatically generate dense, time-aligned video captions, as well as tough question answer decoy sets for video segments (up to 15 minutes in length). Our dataset Neptune covers a broad range of long video reasoning abilities and consists of a subset that emphasizes multimodal reasoning. Since existing metrics for open-ended question answering are either rule-based or may rely on proprietary models, we provide a new open source model-based metric GEM to score open-ended responses on Neptune. Benchmark evaluations reveal that most current open-source long video models perform poorly on Neptune, particularly on questions testing temporal ordering, counting and state changes. Through Neptune, we aim to spur the development of more advanced models capable of understanding long videos. The dataset is available at https://github.com/google-deepmind/neptune

Visual Lexicon: Rich Image Features in Language Space

We present Visual Lexicon, a novel visual language that encodes rich image information into the text space of vocabulary tokens while retaining intricate visual details that are often challenging to convey in natural language. Unlike traditional methods that prioritize either high-level semantics (e.g., CLIP) or pixel-level reconstruction (e.g., VAE), ViLex simultaneously captures rich semantic content and fine visual details, enabling high-quality image generation and comprehensive visual scene understanding. Through a self-supervised learning pipeline, ViLex generates tokens optimized for reconstructing input images using a frozen text-to-image (T2I) diffusion model, preserving the detailed information necessary for high-fidelity semantic-level reconstruction. As an image embedding in the language space, ViLex tokens leverage the compositionality of natural languages, allowing them to be used independently as "text tokens" or combined with natural language tokens to prompt pretrained T2I models with both visual and textual inputs, mirroring how we interact with vision-language models (VLMs). Experiments demonstrate that ViLex achieves higher fidelity in image reconstruction compared to text embeddings--even with a single ViLex token. Moreover, ViLex successfully performs various DreamBooth tasks in a zero-shot, unsupervised manner without fine-tuning T2I models. Additionally, ViLex serves as a powerful vision encoder, consistently improving vision-language model performance across 15 benchmarks relative to a strong SigLIP baseline.

STT: Stateful Tracking with Transformers for Autonomous Driving

Tracking objects in three-dimensional space is critical for autonomous driving. To ensure safety while driving, the tracker must be able to reliably track objects across frames and accurately estimate their states such as velocity and acceleration in the present. Existing works frequently focus on the association task while either neglecting the model performance on state estimation or deploying complex heuristics to predict the states. In this paper, we propose STT, a Stateful Tracking model built with Transformers, that can consistently track objects in the scenes while also predicting their states accurately. STT consumes rich appearance, geometry, and motion signals through long term history of detections and is jointly optimized for both data association and state estimation tasks. Since the standard tracking metrics like MOTA and MOTP do not capture the combined performance of the two tasks in the wider spectrum of object states, we extend them with new metrics called S-MOTA and MOTPS that address this limitation. STT achieves competitive real-time performance on the Waymo Open Dataset.

Streaming Dense Video Captioning

An ideal model for dense video captioning -- predicting captions localized temporally in a video -- should be able to handle long input videos, predict rich, detailed textual descriptions, and be able to produce outputs before processing the entire video. Current state-of-the-art models, however, process a fixed number of downsampled frames, and make a single full prediction after seeing the whole video. We propose a streaming dense video captioning model that consists of two novel components: First, we propose a new memory module, based on clustering incoming tokens, which can handle arbitrarily long videos as the memory is of a fixed size. Second, we develop a streaming decoding algorithm that enables our model to make predictions before the entire video has been processed. Our model achieves this streaming ability, and significantly improves the state-of-the-art on three dense video captioning benchmarks: ActivityNet, YouCook2 and ViTT. Our code is released at https://github.com/google-research/scenic.

Distilling Vision-Language Models on Millions of Videos

The recent advance in vision-language models is largely attributed to the abundance of image-text data. We aim to replicate this success for video-language models, but there simply is not enough human-curated video-text data available. We thus resort to fine-tuning a video-language model from a strong image-language baseline with synthesized instructional data. The resulting video-language model is then used to auto-label millions of videos to generate high-quality captions. We show the adapted video-language model performs well on a wide range of video-language benchmarks. For instance, it surpasses the best prior result on open-ended NExT-QA by 2.8%. Besides, our model generates detailed descriptions for previously unseen videos, which provide better textual supervision than existing methods. Experiments show that a video-language dual-encoder model contrastively trained on these auto-generated captions is 3.8% better than the strongest baseline that also leverages vision-language models. Our best model outperforms state-of-the-art methods on MSR-VTT zero-shot text-to-video retrieval by 6%.

Pixel Aligned Language Models

Large language models have achieved great success in recent years, so as their variants in vision. Existing vision-language models can describe images in natural languages, answer visual-related questions, or perform complex reasoning about the image. However, it is yet unclear how localization tasks, such as word grounding or referring localization, can be performed using large language models. In this work, we aim to develop a vision-language model that can take locations, for example, a set of points or boxes, as either inputs or outputs. When taking locations as inputs, the model performs location-conditioned captioning, which generates captions for the indicated object or region. When generating locations as outputs, our model regresses pixel coordinates for each output word generated by the language model, and thus performs dense word grounding. Our model is pre-trained on the Localized Narrative dataset, which contains pixel-word-aligned captioning from human attention. We show our model can be applied to various location-aware vision-language tasks, including referring localization, location-conditioned captioning, and dense object captioning, archiving state-of-the-art performance on RefCOCO and Visual Genome. Project page: https://jerryxu.net/PixelLLM .

MaskConver: Revisiting Pure Convolution Model for Panoptic Segmentation

In recent years, transformer-based models have dominated panoptic segmentation, thanks to their strong modeling capabilities and their unified representation for both semantic and instance classes as global binary masks. In this paper, we revisit pure convolution model and propose a novel panoptic architecture named MaskConver. MaskConver proposes to fully unify things and stuff representation by predicting their centers. To that extent, it creates a lightweight class embedding module that can break the ties when multiple centers co-exist in the same location. Furthermore, our study shows that the decoder design is critical in ensuring that the model has sufficient context for accurate detection and segmentation. We introduce a powerful ConvNeXt-UNet decoder that closes the performance gap between convolution- and transformerbased models. With ResNet50 backbone, our MaskConver achieves 53.6% PQ on the COCO panoptic val set, outperforming the modern convolution-based model, Panoptic FCN, by 9.3% as well as transformer-based models such as Mask2Former (+1.7% PQ) and kMaX-DeepLab (+0.6% PQ). Additionally, MaskConver with a MobileNet backbone reaches 37.2% PQ, improving over Panoptic-DeepLab by +6.4% under the same FLOPs/latency constraints. A further optimized version of MaskConver achieves 29.7% PQ, while running in real-time on mobile devices. The code and model weights will be publicly available

Does Visual Pretraining Help End-to-End Reasoning?

We aim to investigate whether end-to-end learning of visual reasoning can be achieved with general-purpose neural networks, with the help of visual pretraining. A positive result would refute the common belief that explicit visual abstraction (e.g. object detection) is essential for compositional generalization on visual reasoning, and confirm the feasibility of a neural network "generalist" to solve visual recognition and reasoning tasks. We propose a simple and general self-supervised framework which "compresses" each video frame into a small set of tokens with a transformer network, and reconstructs the remaining frames based on the compressed temporal context. To minimize the reconstruction loss, the network must learn a compact representation for each image, as well as capture temporal dynamics and object permanence from temporal context. We perform evaluation on two visual reasoning benchmarks, CATER and ACRE. We observe that pretraining is essential to achieve compositional generalization for end-to-end visual reasoning. Our proposed framework outperforms traditional supervised pretraining, including image classification and explicit object detection, by large margins.

How can objects help action recognition?

Current state-of-the-art video models process a video clip as a long sequence of spatio-temporal tokens. However, they do not explicitly model objects, their interactions across the video, and instead process all the tokens in the video. In this paper, we investigate how we can use knowledge of objects to design better video models, namely to process fewer tokens and to improve recognition accuracy. This is in contrast to prior works which either drop tokens at the cost of accuracy, or increase accuracy whilst also increasing the computation required. First, we propose an object-guided token sampling strategy that enables us to retain a small fraction of the input tokens with minimal impact on accuracy. And second, we propose an object-aware attention module that enriches our feature representation with object information and improves overall accuracy. Our resulting framework achieves better performance when using fewer tokens than strong baselines. In particular, we match our baseline with 30%, 40%, and 60% of the input tokens on SomethingElse, Something-something v2, and Epic-Kitchens, respectively. When we use our model to process the same number of tokens as our baseline, we improve by 0.6 to 4.2 points on these datasets.

Dense Video Object Captioning from Disjoint Supervision

We propose a new task and model for dense video object captioning -- detecting, tracking, and captioning trajectories of all objects in a video. This task unifies spatial and temporal understanding of the video, and requires fine-grained language description. Our model for dense video object captioning is trained end-to-end and consists of different modules for spatial localization, tracking, and captioning. As such, we can train our model with a mixture of disjoint tasks, and leverage diverse, large-scale datasets which supervise different parts of our model. This results in noteworthy zero-shot performance. Moreover, by finetuning a model from this initialization, we can further improve our performance, surpassing strong image-based baselines by a significant margin. Although we are not aware of other work performing this task, we are able to repurpose existing video grounding datasets for our task, namely VidSTG and VLN. We show our task is more general than grounding, and models trained on our task can directly be applied to grounding by finding the bounding box with the maximum likelihood of generating the query sentence. Our model outperforms dedicated, state-of-the-art models for spatial grounding on both VidSTG and VLN.