Generating interaction-centric videos, such as those depicting humans or robots interacting with objects, is crucial for embodied intelligence, as they provide rich and diverse visual priors for robot learning, manipulation policy training, and affordance reasoning. However, existing methods often struggle to model such complex and dynamic interactions. While recent studies show that masks can serve as effective control signals and enhance generation quality, obtaining dense and precise mask annotations remains a major challenge for real-world use. To overcome this limitation, we introduce Mask2IV, a novel framework specifically designed for interaction-centric video generation. It adopts a decoupled two-stage pipeline that first predicts plausible motion trajectories for both actor and object, then generates a video conditioned on these trajectories. This design eliminates the need for dense mask inputs from users while preserving the flexibility to manipulate the interaction process. Furthermore, Mask2IV supports versatile and intuitive control, allowing users to specify the target object of interaction and guide the motion trajectory through action descriptions or spatial position cues. To support systematic training and evaluation, we curate two benchmarks covering diverse action and object categories across both human-object interaction and robotic manipulation scenarios. Extensive experiments demonstrate that our method achieves superior visual realism and controllability compared to existing baselines.

Speech-driven talking heads have recently emerged and enable interactive avatars. However, real-world applications are limited, as current methods achieve high visual fidelity but slow or fast yet temporally unstable. Diffusion methods provide realistic image generation, yet struggle with one-shot settings. Gaussian Splatting approaches are real-time, yet inaccuracies in facial tracking, or inconsistent Gaussian mappings, lead to unstable outputs and video artifacts that are detrimental to realistic use cases. We address this problem by mapping Gaussian Splatting using 3D Morphable Models to generate person-specific avatars. We introduce transformer-based prediction of model parameters, directly from audio, to drive temporal consistency. From monocular video and independent audio speech inputs, our method enables generation of real-time talking head videos where we report competitive quantitative and qualitative performance.

Procedural texts help AI enhance reasoning about context and action sequences. Transforming these into Semantic Role Labeling (SRL) improves understanding of individual steps by identifying predicate-argument structure like verb,what,where/with. Procedural instructions are highly elliptic, for instance, (i) add cucumber to the bowl and (ii) add sliced tomatoes, the second step's where argument is inferred from the context, referring to where the cucumber was placed. Prior SRL benchmarks often miss implicit arguments, leading to incomplete understanding. To address this, we introduce Implicit-VidSRL, a dataset that necessitates inferring implicit and explicit arguments from contextual information in multimodal cooking procedures. Our proposed dataset benchmarks multimodal models' contextual reasoning, requiring entity tracking through visual changes in recipes. We study recent multimodal LLMs and reveal that they struggle to predict implicit arguments of what and where/with from multi-modal procedural data given the verb. Lastly, we propose iSRL-Qwen2-VL, which achieves a 17% relative improvement in F1-score for what-implicit and a 14.7% for where/with-implicit semantic roles over GPT-4o.

Video understanding has made huge strides in recent years, relying largely on the power of transformers. As this architecture is notoriously expensive and video data is highly redundant, research into improving efficiency has become particularly relevant. Some creative solutions include token selection and merging. While most methods succeed in reducing the cost of the model and maintaining accuracy, an interesting pattern arises: most methods do not outperform the baseline of randomly discarding tokens. In this paper we take a closer look at this phenomenon and observe 5 principles of the nature of visual tokens. For example, we observe that the value of tokens follows a clear Pareto-distribution where most tokens have remarkably low value, and just a few carry most of the perceptual information. We build on these and further insights to propose a lightweight video model, LITE, that can select a small number of tokens effectively, outperforming state-of-the-art and existing baselines across datasets (Kinetics-400 and Something-Something-V2) in the challenging trade-off of computation (GFLOPs) vs accuracy. Experiments also show that LITE generalizes across datasets and even other tasks without the need for retraining.

The success of the machine learning field has reliably depended on training on large datasets. While effective, this trend comes at an extraordinary cost. This is due to two deeply intertwined factors: the size of models and the size of datasets. While promising research efforts focus on reducing the size of models, the other half of the equation remains fairly mysterious. Indeed, it is surprising that the standard approach to training remains to iterate over and over, uniformly sampling the training dataset. In this paper we explore a series of alternative training paradigms that leverage insights from hard-data-mining and dropout, simple enough to implement and use that can become the new training standard. The proposed Progressive Data Dropout reduces the number of effective epochs to as little as 12.4\% of the baseline. This savings actually do not come at any cost for accuracy. Surprisingly, the proposed method improves accuracy by up to 4.82\%. Our approach requires no changes to model architecture or optimizer, and can be applied across standard training pipelines, thus posing an excellent opportunity for wide adoption. Code can be found here: \url{https://github.com/bazyagami/LearningWithRevision}.

We introduce One-shot Open Affordance Learning (OOAL), where a model is trained with just one example per base object category, but is expected to identify novel objects and affordances. While vision-language models excel at recognizing novel objects and scenes, they often struggle to understand finer levels of granularity such as affordances. To handle this issue, we conduct a comprehensive analysis of existing foundation models, to explore their inherent understanding of affordances and assess the potential for data-limited affordance learning. We then propose a vision-language framework with simple and effective designs that boost the alignment between visual features and affordance text embeddings. Experiments on two affordance segmentation benchmarks show that the proposed method outperforms state-of-the-art models with less than 1% of the full training data, and exhibits reasonable generalization capability on unseen objects and affordances. Project page: https://reagan1311.github.io/ooal.

Humans excel at acquiring knowledge through observation. For example, we can learn to use new tools by watching demonstrations. This skill is fundamental for intelligent systems to interact with the world. A key step to acquire this skill is to identify what part of the object affords each action, which is called affordance grounding. In this paper, we address this problem and propose a framework called LOCATE that can identify matching object parts across images, to transfer knowledge from images where an object is being used (exocentric images used for learning), to images where the object is inactive (egocentric ones used to test). To this end, we first find interaction areas and extract their feature embeddings. Then we learn to aggregate the embeddings into compact prototypes (human, object part, and background), and select the one representing the object part. Finally, we use the selected prototype to guide affordance grounding. We do this in a weakly supervised manner, learning only from image-level affordance and object labels. Extensive experiments demonstrate that our approach outperforms state-of-the-art methods by a large margin on both seen and unseen objects.11Project page: https://reagan1311.github.io/locate.

The goal of this work is to understand the way actions are performed in videos. That is, given a video, we aim to predict an adverb indicating a modification applied to the action (e.g. cut “finely”). We cast this problem as a regression task. We measure textual relationships between verbs and adverbs to generate a regression target representing the action change we aim to learn. We test our approach on a range of datasets and achieve state-of-the-art results on both adverb prediction and antonym classification. Furthermore, we outperform previous work when we lift two commonly assumed conditions: the availability of action labels during testing and the pairing of adverbs as antonyms. Existing datasets for adverb recognition are either noisy, which makes learning difficult, or contain actions whose appearance is not influenced by adverbs, which makes evaluation less reliable. To address this, we collect a new high quality dataset: Adverbs in Recipes (AIR). We focus on instructional recipes videos, curating a set of actions that exhibit meaningful visual changes when performed differently. Videos in AIR are more tightly trimmed and were manually reviewed by multiple annotators to ensure high labelling quality. Results show that models learn better from AIR given its cleaner videos. At the same time, adverb prediction on AIR is challenging, demonstrating that there is considerable room for improvement.

Video classification is computationally expensive. In this paper, we address theproblem of frame selection to reduce the computational cost of video classification.Recent work has successfully leveraged frame selection for long, untrimmed videos,where much of the content is not relevant, and easy to discard. In this work, however,we focus on the more standard short, trimmed video classification problem. Weargue that good frame selection can not only reduce the computational cost of videoclassification but also increase the accuracy by getting rid of frames that are hard toclassify. In contrast to previous work, we propose a method that instead of selectingframes by considering one at a time, considers them jointly. This results in a moreefficient selection, where “good" frames are more effectively distributed over thevideo, like snapshots that tell a story. We call the proposed frame selection SMARTand we test it in combination with different backbone architectures and on multiplebenchmarks (Kinetics [5], Something-something [14], UCF101 [31]). We showthat the SMART frame selection consistently improves the accuracy compared toother frame selection strategies while reducing the computational cost by a factorof 4 to 10 times. Additionally, we show that when the primary goal is recognitionperformance, our selection strategy can improve over recent state-of-the-art modelsand frame selection strategies on various benchmarks (UCF101, HMDB51 [21],FCVID [17], and ActivityNet [4]).

Prototype learning is extensively used for few-shot segmentation. Typically, a single prototype is obtained from the support feature by averaging the global object information. However, using one prototype to represent all the information may lead to ambiguities. In this paper, we propose two novel modules, named superpixel-guided clustering (SGC) and guided prototype allocation (GPA), for multiple prototype extraction and allocation. Specifically, SGC is a parameter-free and training-free approach, which extracts more representative prototypes by aggregating similar feature vectors, while GPA is able to select matched prototypes to provide more accurate guidance. By integrating the SGC and GPA together, we propose the Adaptive Superpixel-guided Network (ASGNet), which is a lightweight model and adapts to object scale and shape variation. In addition, our network can easily generalize to k-shot segmentation with substantial improvement and no additional computational cost. In particular, our evaluations on COCO demonstrate that ASGNet surpasses the state-of-the-art method by 5% in 5-shot segmentation.1

Understanding temporal information and how the visual world changes over time, is a fundamental ability of intelligent systems. In video understanding, temporal information is at the core of many current challenges, including compression, efficient inference, motion estimation or summarization. However, in current video datasets it has been observed that action classes can often be recognized without any temporal information, from a single frame of video. As a result, both benchmarking and training in these datasets may give an unintentional advantage to models with strong image understanding capabilities, as opposed to those with strong temporal understanding. In other words, current datasets may not reward good temporal understanding, potentially hindering progress. In this paper we address this problem head on by identifying action classes where temporal information is actually necessary to recognize them and call these "temporal classes". Selecting temporal classes using a computational method would bias the process. Instead, we propose a methodology based on a simple and effective human annotation experiment. We remove just the temporal information, by shuffling frames in time, and measure if the action can still be recognized. Classes that cannot be recognized when frames are not in order, are included in the temporal set. We observe that this set is statistically different from other static classes, and that performance in it correlates with a network's ability to capture temporal information. Thus we use it as a benchmark on current popular networks, which reveals a series of interesting facts, like inflated convolutions bias networks towards classes where motion is not important. We also explore the effect of training on the temporal set, and observe that this leads to better generalization in unseen classes, demonstrating the need for more temporal data. We hope that the proposed dataset of temporal categories will help guide future research in temporal modeling for better video understanding.

Typical video classification methods often divide a video into short clips, do inference on each clip independently, then aggregate the clip-level predictions to generate the video-level results. However, processing visually similar clips independently ignores the temporal structure of the video sequence, and increases the computational cost at inference time. In this paper, we propose a novel framework named FASTER, i.e., Feature Aggregation for Spatio-TEmporal Redundancy. FASTER aims to leverage the redundancy between neighboring clips and reduce the computational cost by learning to aggregate the predictions from models of different complexities. The FASTER framework can integrate high quality representations from expensive models to capture subtle motion information and lightweight representations from cheap models to cover scene changes in the video. A new recurrent network (i.e., FAST-GRU) is designed to aggregate the mixture of different representations. Compared with existing approaches, FASTER can reduce the FLOPs by over 10× while maintaining the state-of-the-art accuracy across popular datasets, such as Kinetics, UCF-101 and HMDB-51.

Motion has shown to be useful for video understanding, where motion is typically represented by optical flow. However, computing flow from video frames is very timeconsuming. Recent works directly leverage the motion vectors and residuals readily available in the compressed video to represent motion at no cost. While this avoids flow computation, it also hurts accuracy since the motion vector is noisy and has substantially reduced resolution, which makes it a less discriminative motion representation. To remedy these issues, we propose a lightweight generator network, which reduces noises in motion vectors and captures fine motion details, achieving a more Discriminative Motion Cue (DMC) representation. Since optical flow is a more accurate motion representation, we train the DMC generator to approximate flow using a reconstruction loss and a generative adversarial loss, jointly with the downstream action classification task. Extensive evaluations on three action recognition benchmarks (HMDB-51, UCF-101, and a subset of Kinetics) confirm the effectiveness of our method. Our full system, consisting of the generator and the classifier, is coined as DMC-Net which obtains high accuracy close to that of using flow and runs two orders of magnitude faster than using optical flow at inference time.

The optical flow of natural scenes is a combination of the motion of the observer and the independent motion of objects. Existing algorithms typically focus on either recovering motion and structure under the assumption of a purely static world or optical flow for general unconstrained scenes. We combine these approaches in an optical flow algorithm that estimates an explicit segmentation of moving objects from appearance and physical constraints. In static regions we take advantage of strong constraints to jointly estimate the camera motion and the 3D structure of the scene over multiple frames. This allows us to also regularize the structure instead of the motion. Our formulation uses a Plane+Parallax framework, which works even under small baselines, and reduces the motion estimation to a one-dimensional search problem, resulting in more accurate estimation. In moving regions the flow is treated as unconstrained, and computed with an existing optical flow method. The resulting Mostly-Rigid Flow (MR-Flow) method achieves state-of-the-art results on both the MPI-Sintel and KITTI-2015 benchmarks.

Existing optical flow methods make generic, spatially homogeneous, assumptions about the spatial structure of the flow. In reality, optical flow varies across an image depending on object class. Simply put, different objects move differently. Here we exploit recent advances in static semantic scene segmentation to segment the image into objects of different types. We define different models of image motion in these regions depending on the type of object. For example, we model the motion on roads with homographies, vegetation with spatially smooth flow, and independently moving objects like cars and planes with affine motion plus deviations. We then pose the flow estimation problem using a novel formulation of localized layers, which addresses limitations of traditional layered models for dealing with complex scene motion. Our semantic flow method achieves the lowest error of any published monocular method in the KITTI-2015 flow benchmark and produces qualitatively better flow and segmentation than recent top methods on a wide range of natural videos.

Abstract Converting unconstrained video sequences into videos that loop seamlessly is an extremely challenging problem. In this work, we take the first steps towards automating this process by focusing on an important subclass of videos containing a single dominant foreground object. Our technique makes two novel contributions over previous work: first, we propose a correspondence‐based similarity metric to automatically identify a good transition point in the video where the appearance and dynamics of the foreground are most consistent. Second, we develop a technique that aligns both the foreground and background about this transition point using a combination of global camera path planning and patch‐based video morphing. We demonstrate that this allows us to create natural, compelling, loopy videos from a wide range of videos collected from the internet.

While region-based image alignment algorithms that use gradient descent can achieve sub-pixel accuracy when they converge, their convergence depends on the smoothness of the image intensity values.Image smoothness is often enforced through the use of multiscale approaches in which images are smoothed and downsampled.Yet, these approaches typically use fixed smoothing parameters which may be appropriate for some images but not for others.Even for a particular image, the optimal smoothing parameters may depend on the magnitude of the transformation.When the transformation is large, the image should be smoothed more than when the transformation is small.Further, with gradient-based approaches, the optimal smoothing parameters may change with each iteration as the algorithm proceeds towards convergence.We address convergence issues related to the choice of smoothing parameters by deriving a Gauss-Newton gradient descent algorithm based on distribution fields (DFs) and proposing a method to dynamically select smoothing parameters at each iteration.DF and DF-like representations have previously been used in the context of tracking.In this work we incorporate DFs into a full affine model for region-based alignment and simultaneously search over parameterized sets of geometric and photometric transforms.We use a probabilistic interpretation of DFs to select smoothing parameters at each step in the optimization and show that this results in improved convergence rates.

Visual tracking of general objects often relies on the assumption that gradient descent of the alignment function will reach the global optimum. A common technique to smooth the objective function is to blur the image. However, blurring the image destroys image information, which can cause the target to be lost. To address this problem we introduce a method for building an image descriptor using distribution fields (DFs), a representation that allows smoothing the objective function without destroying information about pixel values. We present experimental evidence on the superiority of the width of the basin of attraction around the global optimum of DFs over other descriptors. DFs also allow the representation of uncertainty about the tracked object. This helps in disregarding outliers during tracking (like occlusions or small misalignments) without modeling them explicitly. Finally, this provides a convenient way to aggregate the observations of the object through time and maintain an updated model. We present a simple tracking algorithm that uses DFs and obtains state-of-the-art results on standard benchmarks.