It's Just Another Day: Unique Video Captioning by Discriminative Prompting

Long videos contain many repeating actions, events and shots. These repetitions are frequently given identical captions, which makes it difficult to retrieve the exact desired clip using a text search. In this paper, we formulate the problem of unique captioning: Given multiple clips with the same caption, we generate a new caption for each clip that uniquely identifies it. We propose Captioning by Discriminative Prompting (CDP), which predicts a property that can separate identically captioned clips, and use it to generate unique captions. We introduce two benchmarks for unique captioning, based on egocentric footage and timeloop movies - where repeating actions are common. We demonstrate that captions generated by CDP improve text-to-video R@1 by 15% for egocentric videos and 10% in timeloop movies.

AMEGO: Active Memory from long EGOcentric videos

Egocentric videos provide a unique perspective into individuals' daily experiences, yet their unstructured nature presents challenges for perception. In this paper, we introduce AMEGO, a novel approach aimed at enhancing the comprehension of very-long egocentric videos. Inspired by the human's ability to maintain information from a single watching, AMEGO focuses on constructing a self-contained representations from one egocentric video, capturing key locations and object interactions. This representation is semantic-free and facilitates multiple queries without the need to reprocess the entire visual content. Additionally, to evaluate our understanding of very-long egocentric videos, we introduce the new Active Memories Benchmark (AMB), composed of more than 20K of highly challenging visual queries from EPIC-KITCHENS. These queries cover different levels of video reasoning (sequencing, concurrency and temporal grounding) to assess detailed video understanding capabilities. We showcase improved performance of AMEGO on AMB, surpassing other video QA baselines by a substantial margin.

Rank2Reward: Learning Shaped Reward Functions from Passive Video

Teaching robots novel skills with demonstrations via human-in-the-loop data collection techniques like kinesthetic teaching or teleoperation puts a heavy burden on human supervisors. In contrast to this paradigm, it is often significantly easier to provide raw, action-free visual data of tasks being performed. Moreover, this data can even be mined from video datasets or the web. Ideally, this data can serve to guide robot learning for new tasks in novel environments, informing both "what" to do and "how" to do it. A powerful way to encode both the "what" and the "how" is to infer a well-shaped reward function for reinforcement learning. The challenge is determining how to ground visual demonstration inputs into a well-shaped and informative reward function. We propose a technique Rank2Reward for learning behaviors from videos of tasks being performed without access to any low-level states and actions. We do so by leveraging the videos to learn a reward function that measures incremental "progress" through a task by learning how to temporally rank the video frames in a demonstration. By inferring an appropriate ranking, the reward function is able to guide reinforcement learning by indicating when task progress is being made. This ranking function can be integrated into an adversarial imitation learning scheme resulting in an algorithm that can learn behaviors without exploiting the learned reward function. We demonstrate the effectiveness of Rank2Reward at learning behaviors from raw video on a number of tabletop manipulation tasks in both simulations and on a real-world robotic arm. We also demonstrate how Rank2Reward can be easily extended to be applicable to web-scale video datasets.

HOI-Ref: Hand-Object Interaction Referral in Egocentric Vision

Large Vision Language Models (VLMs) are now the de facto state-of-the-art for a number of tasks including visual question answering, recognising objects, and spatial referral. In this work, we propose the HOI-Ref task for egocentric images that aims to understand interactions between hands and objects using VLMs. To enable HOI-Ref, we curate the HOI-QA dataset that consists of 3.9M question-answer pairs for training and evaluating VLMs. HOI-QA includes questions relating to locating hands, objects, and critically their interactions (e.g. referring to the object being manipulated by the hand). We train the first VLM for HOI-Ref on this dataset and call it VLM4HOI. Our results demonstrate that VLMs trained for referral on third person images fail to recognise and refer hands and objects in egocentric images. When fine-tuned on our egocentric HOI-QA dataset, performance improves by 27.9% for referring hands and objects, and by 26.7% for referring interactions.

TIM: A Time Interval Machine for Audio-Visual Action Recognition

Diverse actions give rise to rich audio-visual signals in long videos. Recent works showcase that the two modalities of audio and video exhibit different temporal extents of events and distinct labels. We address the interplay between the two modalities in long videos by explicitly modelling the temporal extents of audio and visual events. We propose the Time Interval Machine (TIM) where a modality-specific time interval poses as a query to a transformer encoder that ingests a long video input. The encoder then attends to the specified interval, as well as the surrounding context in both modalities, in order to recognise the ongoing action. We test TIM on three long audio-visual video datasets: EPIC-KITCHENS, Perception Test, and AVE, reporting state-of-the-art (SOTA) for recognition. On EPIC-KITCHENS, we beat previous SOTA that utilises LLMs and significantly larger pre-training by 2.9% top-1 action recognition accuracy. Additionally, we show that TIM can be adapted for action detection, using dense multi-scale interval queries, outperforming SOTA on EPIC-KITCHENS-100 for most metrics, and showing strong performance on the Perception Test. Our ablations show the critical role of integrating the two modalities and modelling their time intervals in achieving this performance. Code and models at: https://github.com/JacobChalk/TIM

Spatial Cognition from Egocentric Video: Out of Sight, Not Out of Mind

As humans move around, performing their daily tasks, they are able to recall where they have positioned objects in their environment, even if these objects are currently out of sight. In this paper, we aim to mimic this spatial cognition ability. We thus formulate the task of Out of Sight, Not Out of Mind - 3D tracking active objects using observations captured through an egocentric camera. We introduce Lift, Match and Keep (LMK), a method which lifts partial 2D observations to 3D world coordinates, matches them over time using visual appearance, 3D location and interactions to form object tracks, and keeps these object tracks even when they go out-of-view of the camera - hence keeping in mind what is out of sight. We test LMK on 100 long videos from EPIC-KITCHENS. Our results demonstrate that spatial cognition is critical for correctly locating objects over short and long time scales. E.g., for one long egocentric video, we estimate the 3D location of 50 active objects. Of these, 60% can be correctly positioned in 3D after 2 minutes of leaving the camera view.

Every Shot Counts: Using Exemplars for Repetition Counting in Videos

Video repetition counting infers the number of repetitions of recurring actions or motion within a video. We propose an exemplar-based approach that discovers visual correspondence of video exemplars across repetitions within target videos. Our proposed Every Shot Counts (ESCounts) model is an attention-based encoder-decoder that encodes videos of varying lengths alongside exemplars from the same and different videos. In training, ESCounts regresses locations of high correspondence to the exemplars within the video. In tandem, our method learns a latent that encodes representations of general repetitive motions, which we use for exemplar-free, zero-shot inference. Extensive experiments over commonly used datasets (RepCount, Countix, and UCFRep) showcase ESCounts obtaining state-of-the-art performance across all three datasets. On RepCount, ESCounts increases the off-by-one from 0.39 to 0.56 and decreases the mean absolute error from 0.38 to 0.21. Detailed ablations further demonstrate the effectiveness of our method.

Video Editing for Video Retrieval

Though pre-training vision-language models have demonstrated significant benefits in boosting video-text retrieval performance from large-scale web videos, fine-tuning still plays a critical role with manually annotated clips with start and end times, which requires considerable human effort. To address this issue, we explore an alternative cheaper source of annotations, single timestamps, for video-text retrieval. We initialise clips from timestamps in a heuristic way to warm up a retrieval model. Then a video clip editing method is proposed to refine the initial rough boundaries to improve retrieval performance. A student-teacher network is introduced for video clip editing. The teacher model is employed to edit the clips in the training set whereas the student model trains on the edited clips. The teacher weights are updated from the student's after the student's performance increases. Our method is model agnostic and applicable to any retrieval models. We conduct experiments based on three state-of-the-art retrieval models, COOT, VideoCLIP and CLIP4Clip. Experiments conducted on three video retrieval datasets, YouCook2, DiDeMo and ActivityNet-Captions show that our edited clips consistently improve retrieval performance over initial clips across all the three retrieval models.

Get a Grip: Reconstructing Hand-Object Stable Grasps in Egocentric Videos

We address in-the-wild hand-object reconstruction for a known object category in egocentric videos, focusing on temporal periods of stable grasps. We propose the task of Hand-Object Stable Grasp Reconstruction (HO-SGR), the joint reconstruction of frames during which the hand is stably holding the object. We thus can constrain the object motion relative to the hand, effectively regularising the reconstruction and improving performance. By analysing the 3D ARCTIC dataset, we identify temporal periods where the contact area between the hand and object vertices remain stable. We showcase that objects within stable grasps move within a single degree of freedom (1~DoF). We thus propose a method for jointly optimising all frames within a stable grasp by minimising the object's rotation to that within a latent 1 DoF. We then extend this knowledge to in-the-wild egocentric videos by labelling 2.4K clips of stable grasps from the EPIC-KITCHENS dataset. Our proposed EPIC-Grasps dataset includes 390 object instances of 9 categories, featuring stable grasps from videos of daily interactions in 141 environments. Our method achieves significantly better HO-SGR, both qualitatively and by computing the stable grasp area and 2D projection labels of mask overlaps.

Perception Test 2023: A Summary of the First Challenge And Outcome

The First Perception Test challenge was held as a half-day workshop alongside the IEEE/CVF International Conference on Computer Vision (ICCV) 2023, with the goal of benchmarking state-of-the-art video models on the recently proposed Perception Test benchmark. The challenge had six tracks covering low-level and high-level tasks, with both a language and non-language interface, across video, audio, and text modalities, and covering: object tracking, point tracking, temporal action localisation, temporal sound localisation, multiple-choice video question-answering, and grounded video question-answering. We summarise in this report the task descriptions, metrics, baselines, and results.