Two years ago, Stable Diffusion achieved super-human performance at generating images with super-human numbers of fingers. Following the steady decline of its technical novelty, we propose Stale Diffusion, a method that solidifies and ossifies Stable Diffusion in a maximum-entropy state. Stable Diffusion works analogously to a barn (the Stable) from which an infinite set of horses have escaped (the Diffusion). As the horses have long left the barn, our proposal may be seen as antiquated and irrelevant. Nevertheless, we vigorously defend our claim of novelty by identifying as early adopters of the Slow Science Movement, which will produce extremely important pearls of wisdom in the future. Our speed of contributions can also be seen as a quasi-static implementation of the recent call to pause AI experiments, which we wholeheartedly support. As a result of a careful archaeological expedition to 18-months-old Git commit histories, we found that naturally-accumulating errors have produced a novel entropy-maximising Stale Diffusion method, that can produce sleep-inducing hyper-realistic 5D video that is as good as one's imagination.
In this paper, we consider the problem of temporally aligning the video and texts from instructional videos, specifically, given a long-term video, and associated text sentences, our goal is to determine their corresponding timestamps in the video. To this end, we establish a simple, yet strong model that adopts a Transformer-based architecture with all texts as queries, iteratively attending to the visual features, to infer the optimal timestamp. We conduct thorough experiments to investigate: (i) the effect of upgrading ASR systems to reduce errors from speech recognition, (ii) the effect of various visual-textual backbones, ranging from CLIP to S3D, to the more recent InternVideo, (iii) the effect of transforming noisy ASR transcripts into descriptive steps by prompting a large language model (LLM), to summarize the core activities within the ASR transcript as a new training dataset. As a result, our proposed simple model demonstrates superior performance on both narration alignment and procedural step grounding tasks, surpassing existing state-of-the-art methods by a significant margin on three public benchmarks, namely, 9.3% on HT-Step, 3.4% on HTM-Align and 4.7% on CrossTask. We believe the proposed model and dataset with descriptive steps can be treated as a strong baseline for future research in temporal video-text alignment. All codes, models, and the resulting dataset will be publicly released to the research community.
Audio Description (AD) is the task of generating descriptions of visual content, at suitable time intervals, for the benefit of visually impaired audiences. For movies, this presents notable challenges -- AD must occur only during existing pauses in dialogue, should refer to characters by name, and ought to aid understanding of the storyline as a whole. To this end, we develop a new model for automatically generating movie AD, given CLIP visual features of the frames, the cast list, and the temporal locations of the speech; addressing all three of the 'who', 'when', and 'what' questions: (i) who -- we introduce a character bank consisting of the character's name, the actor that played the part, and a CLIP feature of their face, for the principal cast of each movie, and demonstrate how this can be used to improve naming in the generated AD; (ii) when -- we investigate several models for determining whether an AD should be generated for a time interval or not, based on the visual content of the interval and its neighbours; and (iii) what -- we implement a new vision-language model for this task, that can ingest the proposals from the character bank, whilst conditioning on the visual features using cross-attention, and demonstrate how this improves over previous architectures for AD text generation in an apples-to-apples comparison.
While recent supervised methods for reference-based object counting continue to improve the performance on benchmark datasets, they have to rely on small datasets due to the cost associated with manually annotating dozens of objects in images. We propose Unsupervised Counter (UnCo), a model that can learn this task without requiring any manual annotations. To this end, we construct "SelfCollages", images with various pasted objects as training samples, that provide a rich learning signal covering arbitrary object types and counts. Our method builds on existing unsupervised representations and segmentation techniques to successfully demonstrate the ability to count objects without manual supervision. Our experiments show that our method not only outperforms simple baselines and generic models such as FasterRCNN, but also matches the performance of supervised counting models in some domains.
Our objective is open-world object counting in images, where the target object class is specified by a text description. To this end, we propose CounTX, a class-agnostic, single-stage model using a transformer decoder counting head on top of pre-trained joint text-image representations. CounTX is able to count the number of instances of any class given only an image and a text description of the target object class, and can be trained end-to-end. To the best of our knowledge, we are the first to tackle the open-world counting problem in this way. In addition to this model, we make the following contributions: (i) we compare the performance of CounTX to prior work on open-world object counting, and show that our approach exceeds the state of the art on all measures on the FSC-147 benchmark for methods that use text to specify the task; (ii) we present and release FSC-147-D, an enhanced version of FSC-147 with text descriptions, so that object classes can be described with more detailed language than their simple class names. FSC-147-D is available at https://github.com/niki-amini-naieni/CounTX/.
The objective of this paper is an automatic Audio Description (AD) model that ingests movies and outputs AD in text form. Generating high-quality movie AD is challenging due to the dependency of the descriptions on context, and the limited amount of training data available. In this work, we leverage the power of pretrained foundation models, such as GPT and CLIP, and only train a mapping network that bridges the two models for visually-conditioned text generation. In order to obtain high-quality AD, we make the following four contributions: (i) we incorporate context from the movie clip, AD from previous clips, as well as the subtitles; (ii) we address the lack of training data by pretraining on large-scale datasets, where visual or contextual information is unavailable, e.g. text-only AD without movies or visual captioning datasets without context; (iii) we improve on the currently available AD datasets, by removing label noise in the MAD dataset, and adding character naming information; and (iv) we obtain strong results on the movie AD task compared with previous methods.
Large-scale, weakly-supervised speech recognition models, such as Whisper, have demonstrated impressive results on speech recognition across domains and languages. However, their application to long audio transcription via buffered or sliding window approaches is prone to drifting, hallucination & repetition; and prohibits batched transcription due to their sequential nature. Further, timestamps corresponding each utterance are prone to inaccuracies and word-level timestamps are not available out-of-the-box. To overcome these challenges, we present WhisperX, a time-accurate speech recognition system with word-level timestamps utilising voice activity detection and forced phoneme alignment. In doing so, we demonstrate state-of-the-art performance on long-form transcription and word segmentation benchmarks. Additionally, we show that pre-segmenting audio with our proposed VAD Cut & Merge strategy improves transcription quality and enables a twelve-fold transcription speedup via batched inference.
Large-scale pretrained models, especially those trained from vision-language data have demonstrated the tremendous value that can be gained from both larger training datasets and models. Thus, in order to benefit from these developments, there is renewed interest in transfer learning and adapting models from large-scale general pretraining to particular downstream tasks. However, the continuously increasing size of the models means that even the classic approach of finetuning is becoming infeasible for all but big institutions. Prompt leaning has emerged as a flexible way to adapt models by solely learning additional inputs to a model that is kept frozen, but so far performances remained inferior to finetuning. To address this, we propose the Prompt Generation Network (PGN) that generates input-dependent prompts by sampling from a learned library of tokens. We show the PGN is effective in adapting pretrained models to various new datasets. It surpasses previous prompt-learning methods by a large margin and even fullfinetuning on 5 out of 12 datasets while requiring 100x less parameters. PGN can even be used for training and inferring on multiple datasets simultaneously and learns to allocate tokens between domains. Given these findings, we conclude that PGN is a viable and scalable approach for downstream adaptation of frozen models. Code is available at https://github.com/jochemloedeman/PGN.
The objective of this paper is an efficient training method for video tasks. We make three contributions: (1) We propose Turbo training, a simple and versatile training paradigm for Transformers on multiple video tasks. (2) We illustrate the advantages of Turbo training on action classification, video-language representation learning, and long-video activity classification, showing that Turbo training can largely maintain competitive performance while achieving almost 4X speed-up and significantly less memory consumption. (3) Turbo training enables long-schedule video-language training and end-to-end long-video training, delivering competitive or superior performance than previous works, which were infeasible to train under limited resources.
Building models that can be rapidly adapted to numerous tasks using only a handful of annotated examples is an open challenge for multimodal machine learning research. We introduce Flamingo, a family of Visual Language Models (VLM) with this ability. Flamingo models include key architectural innovations to: (i) bridge powerful pretrained vision-only and language-only models, (ii) handle sequences of arbitrarily interleaved visual and textual data, and (iii) seamlessly ingest images or videos as inputs. Thanks to their flexibility, Flamingo models can be trained on large-scale multimodal web corpora containing arbitrarily interleaved text and images, which is key to endow them with in-context few-shot learning capabilities. We perform a thorough evaluation of the proposed Flamingo models, exploring and measuring their ability to rapidly adapt to a variety of image and video understanding benchmarks. These include open-ended tasks such as visual question-answering, where the model is prompted with a question which it has to answer, captioning tasks, which evaluate the ability to describe a scene or an event, and close-ended tasks such as multiple choice visual question-answering. For tasks lying anywhere on this spectrum, we demonstrate that a single Flamingo model can achieve a new state of the art for few-shot learning, simply by prompting the model with task-specific examples. On many of these benchmarks, Flamingo actually surpasses the performance of models that are fine-tuned on thousands of times more task-specific data.