arXiv subjects

Irfan Essa

Publications and source records attributed to Irfan Essa.

At least 19 recordsLinked to original sources

arXiv2026

MoCHA: Denoising Caption Supervision for Motion-Text Retrieval

Text-motion retrieval systems learn shared embedding spaces from motion-caption pairs via contrastive objectives. However, each caption is not a deterministic label but a sample from a distribution of valid descriptions: different annotators produce different text for the same motion, mixing motion-recoverable semantics (action type, body parts, directionality) with annotator-specific style and inferred context that cannot be determined from 3D joint coordinates alone. Standard contrastive training treats each caption as the single positive target, overlooking this distributional structure and inducing within-motion embedding variance that weakens alignment. We propose MoCHA, a text canonicalization framework that reduces this variance by projecting each caption onto its motion-recoverable content prior to encoding, producing tighter positive clusters and better-separated embeddings. Canonicalization is a general principle: even deterministic rule-based methods improve cross-dataset transfer, though learned canonicalizers provide substantially larger gains. We present two learned variants: an LLM-based approach (GPT-5.2) and a distilled FlanT5 model requiring no LLM at inference time. MoCHA operates as a preprocessing step compatible with any retrieval architecture. Applied to MoPa (MotionPatches), MoCHA sets a new state of the art on both HumanML3D (H) and KIT-ML (K): the LLM variant achieves 13.9% T2M R@1 on H (+3.1pp) and 24.3% on K (+10.3pp), while the LLM-free T5 variant achieves gains of +2.5pp and +8.1pp. Canonicalization reduces within-motion text-embedding variance by 11-19% and improves cross-dataset transfer substantially, with H to K improving by 94% and K to H by 52%, demonstrating that standardizing the language space yields more transferable motion-language representations.

cs.CV↗

arXiv2025

MapReduce LoRA: Advancing the Pareto Front in Multi-Preference Optimization for Generative Models

Reinforcement learning from human feedback (RLHF) with reward models has advanced alignment of generative models to human aesthetic and perceptual preferences. However, jointly optimizing multiple rewards often incurs an alignment tax, improving one dimension while degrading others. To address this, we introduce two complementary methods: MapReduce LoRA and Reward-aware Token Embedding (RaTE). MapReduce LoRA trains preference-specific LoRA experts in parallel and iteratively merges them to refine a shared base model; RaTE learns reward-specific token embeddings that compose at inference for flexible preference control. Experiments on Text-to-Image generation (Stable Diffusion 3.5 Medium and FLUX.1-dev) show improvements of 36.1%, 4.6%, and 55.7%, and 32.7%, 4.3%, and 67.1% on GenEval, PickScore, and OCR, respectively. On Text-to-Video generation (HunyuanVideo), visual and motion quality improve by 48.1% and 90.0%, respectively. On the language task, Helpful Assistant, with Llama-2 7B, helpful and harmless improve by 43.4% and 136.7%, respectively. Our framework sets a new state-of-the-art multi-preference alignment recipe across modalities.

cs.CV↗

arXiv2025

AugLift: Depth-Aware Input Reparameterization Improves Domain Generalization in 2D-to-3D Pose Lifting

Lifting-based 3D human pose estimation infers 3D joints from 2D keypoints but generalizes poorly because $(x,y)$ coordinates alone are an ill-posed, sparse representation that discards geometric information modern foundation models can recover. We propose \emph{AugLift}, which changes the representation format of lifting from 2D coordinates to a 6D geometric descriptor via two modules: (1) an \emph{Uncertainty-Aware Depth Descriptor} (UADD) -- a compact tuple $(c, d, d_{\min}, d_{\max})$ extracted from a confidence-scaled neighborhood of an off-the-shelf monocular depth map -- and (2) a scale normalization component that handles train/test distance shifts. AugLift requires no new sensors, no new data collection, and no architectural changes beyond widening the input layer; because it operates at the representation level, it is composable with any lifting architecture or domain generalization technique. In the detection setting, AugLift reduces cross-dataset MPJPE by $10.1$% on average across four datasets and four lifting architectures while improving in-distribution accuracy by $4.0$%; post-hoc analysis shows gains concentrate on novel poses and occluded joints. In the ground-truth 2D setting, combining AugLift with PoseAug's differentiable domain generalization achieves state-of-the-art cross-dataset performance ($62.4$\,mm on 3DHP, $92.6$\,mm on 3DPW; $14.5$% and $22.2$% over PoseAug), demonstrating that foundation-model depth provides genuine geometric signal complementary to explicit 3D augmentation. Code will be made publicly available.

cs.CV↗

arXiv2025

HierSum: A Global and Local Attention Mechanism for Video Summarization

Video summarization creates an abridged version (i.e., a summary) that provides a quick overview of the video while retaining pertinent information. In this work, we focus on summarizing instructional videos and propose a method for breaking down a video into meaningful segments, each corresponding to essential steps in the video. We propose \textbf{HierSum}, a hierarchical approach that integrates fine-grained local cues from subtitles with global contextual information provided by video-level instructions. Our approach utilizes the ``most replayed" statistic as a supervisory signal to identify critical segments, thereby improving the effectiveness of the summary. We evaluate on benchmark datasets such as TVSum, BLiSS, Mr.HiSum, and the WikiHow test set, and show that HierSum consistently outperforms existing methods in key metrics such as F1-score and rank correlation. We also curate a new multi-modal dataset using WikiHow and EHow videos and associated articles containing step-by-step instructions. Through extensive ablation studies, we demonstrate that training on this dataset significantly enhances summarization on the target datasets.

cs.CV↗

arXiv2025

HALO: Human-Aligned End-to-end Image Retargeting with Layered Transformations

Image retargeting aims to change the aspect-ratio of an image while maintaining its content and structure with less visual artifacts. Existing methods still generate many artifacts or fail to maintain original content or structure. To address this, we introduce HALO, an end-to-end trainable solution for image retargeting. Since humans are more sensitive to distortions in salient areas than non-salient areas of an image, HALO decomposes the input image into salient/non-salient layers and applies different wrapping fields to different layers. To further minimize the structure distortion in the output images, we propose perceptual structure similarity loss which measures the structure similarity between input and output images and aligns with human perception. Both quantitative results and a user study on the RetargetMe dataset show that HALO achieves SOTA. Especially, our method achieves an 18.4% higher user preference compared to the baselines on average.

cs.CV↗

arXiv2025

Leveraging Procedural Knowledge and Task Hierarchies for Efficient Instructional Video Pre-training

Instructional videos provide a convenient modality to learn new tasks (ex. cooking a recipe, or assembling furniture). A viewer will want to find a corresponding video that reflects both the overall task they are interested in as well as contains the relevant steps they need to carry out the task. To perform this, an instructional video model should be capable of inferring both the tasks and the steps that occur in an input video. Doing this efficiently and in a generalizable fashion is key when compute or relevant video topics used to train this model are limited. To address these requirements we explicitly mine task hierarchies and the procedural steps associated with instructional videos. We use this prior knowledge to pre-train our model, $\texttt{Pivot}$, for step and task prediction. During pre-training, we also provide video augmentation and early stopping strategies to optimally identify which model to use for downstream tasks. We test this pre-trained model on task recognition, step recognition, and step prediction tasks on two downstream datasets. When pre-training data and compute are limited, we outperform previous baselines along these tasks. Therefore, leveraging prior task and step structures enables efficient training of $\texttt{Pivot}$ for instructional video recommendation.

cs.CV↗

arXiv2025

MALT Diffusion: Memory-Augmented Latent Transformers for Any-Length Video Generation

Diffusion models are successful for synthesizing high-quality videos but are limited to generating short clips (e.g., 2-10 seconds). Synthesizing sustained footage (e.g. over minutes) still remains an open research question. In this paper, we propose MALT Diffusion (using Memory-Augmented Latent Transformers), a new diffusion model specialized for long video generation. MALT Diffusion (or just MALT) handles long videos by subdividing them into short segments and doing segment-level autoregressive generation. To achieve this, we first propose recurrent attention layers that encode multiple segments into a compact memory latent vector; by maintaining this memory vector over time, MALT is able to condition on it and continuously generate new footage based on a long temporal context. We also present several training techniques that enable the model to generate frames over a long horizon with consistent quality and minimal degradation. We validate the effectiveness of MALT through experiments on long video benchmarks. We first perform extensive analysis of MALT in long-contextual understanding capability and stability using popular long video benchmarks. For example, MALT achieves an FVD score of 220.4 on 128-frame video generation on UCF-101, outperforming the previous state-of-the-art of 648.4. Finally, we explore MALT's capabilities in a text-to-video generation setting and show that it can produce long videos compared with recent techniques for long text-to-video generation.

cs.CV↗

arXiv2025

Calibrated Multi-Preference Optimization for Aligning Diffusion Models

Aligning text-to-image (T2I) diffusion models with preference optimization is valuable for human-annotated datasets, but the heavy cost of manual data collection limits scalability. Using reward models offers an alternative, however, current preference optimization methods fall short in exploiting the rich information, as they only consider pairwise preference distribution. Furthermore, they lack generalization to multi-preference scenarios and struggle to handle inconsistencies between rewards. To address this, we present Calibrated Preference Optimization (CaPO), a novel method to align T2I diffusion models by incorporating the general preference from multiple reward models without human annotated data. The core of our approach involves a reward calibration method to approximate the general preference by computing the expected win-rate against the samples generated by the pretrained models. Additionally, we propose a frontier-based pair selection method that effectively manages the multi-preference distribution by selecting pairs from Pareto frontiers. Finally, we use regression loss to fine-tune diffusion models to match the difference between calibrated rewards of a selected pair. Experimental results show that CaPO consistently outperforms prior methods, such as Direct Preference Optimization (DPO), in both single and multi-reward settings validated by evaluation on T2I benchmarks, including GenEval and T2I-Compbench.

cs.CV↗

arXiv2024

Learning Complex Non-Rigid Image Edits from Multimodal Conditioning

In this paper we focus on inserting a given human (specifically, a single image of a person) into a novel scene. Our method, which builds on top of Stable Diffusion, yields natural looking images while being highly controllable with text and pose. To accomplish this we need to train on pairs of images, the first a reference image with the person, the second a "target image" showing the same person (with a different pose and possibly in a different background). Additionally we require a text caption describing the new pose relative to that in the reference image. In this paper we present a novel dataset following this criteria, which we create using pairs of frames from human-centric and action-rich videos and employing a multimodal LLM to automatically summarize the difference in human pose for the text captions. We demonstrate that identity preservation is a more challenging task in scenes "in-the-wild", and especially scenes where there is an interaction between persons and objects. Combining the weak supervision from noisy captions, with robust 2D pose improves the quality of person-object interactions.

cs.CV↗

arXiv2024

AfriMed-QA: A Pan-African, Multi-Specialty, Medical Question-Answering Benchmark Dataset

Recent advancements in large language model(LLM) performance on medical multiple choice question (MCQ) benchmarks have stimulated interest from healthcare providers and patients globally. Particularly in low-and middle-income countries (LMICs) facing acute physician shortages and lack of specialists, LLMs offer a potentially scalable pathway to enhance healthcare access and reduce costs. However, their effectiveness in the Global South, especially across the African continent, remains to be established. In this work, we introduce AfriMed-QA, the first large scale Pan-African English multi-specialty medical Question-Answering (QA) dataset, 15,000 questions (open and closed-ended) sourced from over 60 medical schools across 16 countries, covering 32 medical specialties. We further evaluate 30 LLMs across multiple axes including correctness and demographic bias. Our findings show significant performance variation across specialties and geographies, MCQ performance clearly lags USMLE (MedQA). We find that biomedical LLMs underperform general models and smaller edge-friendly LLMs struggle to achieve a passing score. Interestingly, human evaluations show a consistent consumer preference for LLM answers and explanations when compared with clinician answers.

cs.CL↗

arXiv2024

Exploring Efficient Foundational Multi-modal Models for Video Summarization

Foundational models are able to generate text outputs given prompt instructions and text, audio, or image inputs. Recently these models have been combined to perform tasks on video, such as video summarization. Such video foundation models perform pre-training by aligning outputs from each modality-specific model into the same embedding space. Then the embeddings from each model are used within a language model, which is fine-tuned on a desired instruction set. Aligning each modality during pre-training is computationally expensive and prevents rapid testing of different base modality models. During fine-tuning, evaluation is carried out within in-domain videos where it is hard to understand the generalizability and data efficiency of these methods. To alleviate these issues we propose a plug-and-play video language model. It directly uses the texts generated from each input modality into the language model, avoiding pre-training alignment overhead. Instead of fine-tuning we leverage few-shot instruction adaptation strategies. We compare the performance versus the computational costs for our plug-and-play style method and baseline tuning methods. Finally, we explore the generalizability of each method during domain shift and present insights on what data is useful when training data is limited. Through this analysis, we present practical insights on how to leverage multi-modal foundational models for effective results given realistic compute and data limitations.

cs.CV↗

arXiv2024

Mamba Fusion: Learning Actions Through Questioning

Video Language Models (VLMs) are crucial for generalizing across diverse tasks and using language cues to enhance learning. While transformer-based architectures have been the de facto in vision-language training, they face challenges like quadratic computational complexity, high GPU memory usage, and difficulty with long-term dependencies. To address these limitations, we introduce MambaVL, a novel model that leverages recent advancements in selective state space modality fusion to efficiently capture long-range dependencies and learn joint representations for vision and language data. MambaVL utilizes a shared state transition matrix across both modalities, allowing the model to capture information about actions from multiple perspectives within the scene. Furthermore, we propose a question-answering task that helps guide the model toward relevant cues. These questions provide critical information about actions, objects, and environmental context, leading to enhanced performance. As a result, MambaVL achieves state-of-the-art performance in action recognition on the Epic-Kitchens-100 dataset and outperforms baseline methods in action anticipation.

cs.CV↗

arXiv2024

Limitations in Employing Natural Language Supervision for Sensor-Based Human Activity Recognition -- And Ways to Overcome Them

Cross-modal contrastive pre-training between natural language and other modalities, e.g., vision and audio, has demonstrated astonishing performance and effectiveness across a diverse variety of tasks and domains. In this paper, we investigate whether such natural language supervision can be used for wearable sensor based Human Activity Recognition (HAR), and discover that-surprisingly-it performs substantially worse than standard end-to-end training and self-supervision. We identify the primary causes for this as: sensor heterogeneity and the lack of rich, diverse text descriptions of activities. To mitigate their impact, we also develop strategies and assess their effectiveness through an extensive experimental evaluation. These strategies lead to significant increases in activity recognition, bringing performance closer to supervised and self-supervised training, while also enabling the recognition of unseen activities and cross modal retrieval of videos. Overall, our work paves the way for better sensor-language learning, ultimately leading to the development of foundational models for HAR using wearables.

cs.LG↗

arXiv2024

Cropper: Vision-Language Model for Image Cropping through In-Context Learning

The goal of image cropping is to identify visually appealing crops in an image. Conventional methods are trained on specific datasets and fail to adapt to new requirements. Recent breakthroughs in large vision-language models (VLMs) enable visual in-context learning without explicit training. However, downstream tasks with VLMs remain under explored. In this paper, we propose an effective approach to leverage VLMs for image cropping. First, we propose an efficient prompt retrieval mechanism for image cropping to automate the selection of in-context examples. Second, we introduce an iterative refinement strategy to iteratively enhance the predicted crops. The proposed framework, we refer to as Cropper, is applicable to a wide range of cropping tasks, including free-form cropping, subject-aware cropping, and aspect ratio-aware cropping. Extensive experiments demonstrate that Cropper significantly outperforms state-of-the-art methods across several benchmarks.

cs.CV↗

arXiv2024

CamViG: Camera Aware Image-to-Video Generation with Multimodal Transformers

We extend multimodal transformers to include 3D camera motion as a conditioning signal for the task of video generation. Generative video models are becoming increasingly powerful, thus focusing research efforts on methods of controlling the output of such models. We propose to add virtual 3D camera controls to generative video methods by conditioning generated video on an encoding of three-dimensional camera movement over the course of the generated video. Results demonstrate that we are (1) able to successfully control the camera during video generation, starting from a single frame and a camera signal, and (2) we demonstrate the accuracy of the generated 3D camera paths using traditional computer vision methods.

cs.CV↗

arXiv2024

SLAIM: Robust Dense Neural SLAM for Online Tracking and Mapping

We present SLAIM - Simultaneous Localization and Implicit Mapping. We propose a novel coarse-to-fine tracking model tailored for Neural Radiance Field SLAM (NeRF-SLAM) to achieve state-of-the-art tracking performance. Notably, existing NeRF-SLAM systems consistently exhibit inferior tracking performance compared to traditional SLAM algorithms. NeRF-SLAM methods solve camera tracking via image alignment and photometric bundle-adjustment. Such optimization processes are difficult to optimize due to the narrow basin of attraction of the optimization loss in image space (local minima) and the lack of initial correspondences. We mitigate these limitations by implementing a Gaussian pyramid filter on top of NeRF, facilitating a coarse-to-fine tracking optimization strategy. Furthermore, NeRF systems encounter challenges in converging to the right geometry with limited input views. While prior approaches use a Signed-Distance Function (SDF)-based NeRF and directly supervise SDF values by approximating ground truth SDF through depth measurements, this often results in suboptimal geometry. In contrast, our method employs a volume density representation and introduces a novel KL regularizer on the ray termination distribution, constraining scene geometry to consist of empty space and opaque surfaces. Our solution implements both local and global bundle-adjustment to produce a robust (coarse-to-fine) and accurate (KL regularizer) SLAM solution. We conduct experiments on multiple datasets (ScanNet, TUM, Replica) showing state-of-the-art results in tracking and in reconstruction accuracy.

cs.CV↗

arXiv2024

3D Semantic MapNet: Building Maps for Multi-Object Re-Identification in 3D

We study the task of 3D multi-object re-identification from embodied tours. Specifically, an agent is given two tours of an environment (e.g. an apartment) under two different layouts (e.g. arrangements of furniture). Its task is to detect and re-identify objects in 3D - e.g. a "sofa" moved from location A to B, a new "chair" in the second layout at location C, or a "lamp" from location D in the first layout missing in the second. To support this task, we create an automated infrastructure to generate paired egocentric tours of initial/modified layouts in the Habitat simulator using Matterport3D scenes, YCB and Google-scanned objects. We present 3D Semantic MapNet (3D-SMNet) - a two-stage re-identification model consisting of (1) a 3D object detector that operates on RGB-D videos with known pose, and (2) a differentiable object matching module that solves correspondence estimation between two sets of 3D bounding boxes. Overall, 3D-SMNet builds object-based maps of each layout and then uses a differentiable matcher to re-identify objects across the tours. After training 3D-SMNet on our generated episodes, we demonstrate zero-shot transfer to real-world rearrangement scenarios by instantiating our task in Replica, Active Vision, and RIO environments depicting rearrangements. On all datasets, we find 3D-SMNet outperforms competitive baselines. Further, we show jointly training on real and generated episodes can lead to significant improvements over training on real data alone.

cs.CV↗

arXiv2024

On the Efficacy of Text-Based Input Modalities for Action Anticipation

Anticipating future actions is a highly challenging task due to the diversity and scale of potential future actions; yet, information from different modalities help narrow down plausible action choices. Each modality can provide diverse and often complementary context for the model to learn from. While previous multi-modal methods leverage information from modalities such as video and audio, we primarily explore how text descriptions of actions and objects can also lead to more accurate action anticipation by providing additional contextual cues, e.g., about the environment and its contents. We propose a Multi-modal Contrastive Anticipative Transformer (M-CAT), a video transformer architecture that jointly learns from multi-modal features and text descriptions of actions and objects. We train our model in two stages, where the model first learns to align video clips with descriptions of future actions, and is subsequently fine-tuned to predict future actions. Compared to existing methods, M-CAT has the advantage of learning additional context from two types of text inputs: rich descriptions of future actions during pre-training, and, text descriptions for detected objects and actions during modality feature fusion. Through extensive experimental evaluation, we demonstrate that our model outperforms previous methods on the EpicKitchens datasets, and show that using simple text descriptions of actions and objects aid in more effective action anticipation. In addition, we examine the impact of object and action information obtained via text, and perform extensive ablations.

cs.CV↗